Abson-dev / Machine-Learning-Goodness

The Machine Learning project including ML/DL projects, notebooks, cheat codes of ML/DL, useful information on AI/AGI and codes or snippets/scripts/tasks with tips.

Machine Learning Goodness with various notebooks , ML/DL projects update and AGI/AI tips/cheats.

Overview

With the start of #100DaysOfMLCode challenge this Machine Learning Goodness repository is updated daily with either the completed Jupyter notebooks, Python codes, ML projects, useful ML/DL/NN libraries, cheat codes of ML/DL/NN/AI, useful information such as websites, beneficial learning materials, tips and whatnot not to mention some basic and advanced Python coding.

Table of Contents

• Table of contents
• Worthy Books
• Worthy Tools
• Worthy Repositories
• Notebooks
• Notes
• 100DaysOfMLCode
• Public
• Jupyter in Browser
• Logo
• License

Worthy Books

(Back to top)

Worthy books to hone expertise of ML/DL/NN/AGI, Python Programming, CS fundamentals needed for AI analysis and any useful book for a Developer or ML Engineer.

Number	Title	Description	Link
1	Grokking Algorithms: An illustrated guide for programmers and other curious people	Visualisation of most popular algorithms used in Machine Learning and programming to solve problems	Grokking Algorithms
2	Algorithm Design Manual	Introduction to mathematical analysis of a variety of computer algorithms	Algorithm Design Manual
3	Category Theory for Programmers	Book about Category Theory written on posts from Milewski's programming cafe	Category Theory for Programmers
4	Automated Machine Learning	Book includes overviews of the bread-and-butter techniques we need in AutoML, provides in-depth discussions of existing AutoML systems, and evaluates the state of the art in AutoML	Automated Machine Learning
5	Mathematics for Computer Science	Book by MIT on Mathematics for Computer Science	Mathematics for Computer Science
6	Mathematics for Machine Learning	Book by University of California on Mathematics for Machine Learning	Mathematics for Machine Learning
7	Applied Artificial Intelligence	Book on engineering AI applications	Applied Artificial Intelligence
8	Automating Machine Learning Pipeline	Book-overview of automating ML lifecycle with Databricks Lakehouse platform	Automating Machine Learning Pipeline
9	Machine Learning Yearning	The book for AI Engineers win the era of Deep Learning	Machine Learning Yearning
10	Think Bayes	An introduytion to Bayesian statistics with Python implementation and Jupyter Notebooks	Think Bayes
11	The Ultimate ChatGPT Guide	The book that provides 100 resources to enhance your life with ChatGPT	The Ultimate ChatGPT Guide
12	The Art of ChatGPT Prompting: A Guide to Crafting Clear and Effective Prompts	The book to learn strategies for crafting compelling ChatGPT prompts that drive engaging and informative conversations	The Art of ChatGPT Prompting: A Guide to Crafting Clear and Effective Prompts
13	10 ChatGPT prompts for Software Engineers	The book to learn how to prompt for software engineering tasks	10 ChatGPT prompts for Software Engineers
14	How to Build Your Career in AI	Andrew Ng's insights about learning foundational skills, working on projects, finding jobs, and community in machine	How to Build Your Career in AI

Worthy Tools

(Back to top)

Worthy websites and tools that include cheat codes for Python, Machine Learning, Deep Learning, Neural Networks and what not apart from other worthy tools while you are learning or honing your skills can be found here. Updated constantly when a worthy material is found to be shared on the repository.

Number	Title	Description	Link
1	Python Cheatsheet	The Python Cheatsheet based on the book "Automate the Boring Stuff with Python" and many other sources	Python Cheatsheet
2	Machine Learning Algorithms Cheatsheet	The Machine Learning Cheatsheet explaining various models briefly	ML Algorithms Cheatsheet
3	Awesome AI Datasets & Tools	Links to popular open-source and public datasets, data visualizations, data analytics resources, and data lakes	Awesome AI Datasets & Tools
4	Machine Learning Cheatsheet	This Cheatsheet contains many classical equations and diagrams on Machine Learning to quickly recall knowledge and ideas on Machine Learning	Machine Learning Cheatsheet
5	Universal Intelligence: A Definition of Machine Intelligence	The publication on definitions of intelligence	Universal Intelligence
6	Logistic Regression	Detailed Overview of Logistic Regression	Logistic Regression
7	BCI Overview	Simple Overview of Brain-Computer Interface (BCI)	BCI Overview
8	BCI Research	Fascinating research of Brain-Computer Interface (BCI)	BCI Research
9	AI in Chemical Discovery	How AI is changing Chemical Diccovery?	AI in Chemical Discovery
10	Machine Learning for Chemistry	Best practices in Machine Learning for Chemistry	Machine Learning for Chemistry
11	AI tools for drug discovery	5 cool AI-powered Drug Discovery tools	AI tools for drug discovery
12	Quantum Chemistry and Deep Learning	The application of Deep Learning and Neural Networks on Quantum Chemisty	Quantum Chemistry and Deep Learning
13	Computing Machinery and Intelligence	First paper on AI by Alan Turing	Computing Machinery and Intelligence
14	The blog on the take of Alan Turing	The analysis of Alan Turing's paper on AI (13 in the list) and the blog post on the life of him	Blog on Alan Turing
15	Minds, Brains and Programs	Paper that objects 'Turing Test' by John Searle	Minds, Brains and Programs
16	The blog on the take Of John Searle & Alan Turing	The blog post on the take Of John Searle paper (15 in the list) and ideas about AI and Alan Turing	John Searle & Alan Turing
17	The Youtube channel on Deep Learning's Neural Networks	An amazing youtube channel explaining what is Neural Network with simple and easy to follow descriptions	Deep Learning's Neural Networks
18	8 architectures of Neural Networks	8 architectures of Neural Network every ML engineer should know	8 architectures
19	Neural Networks for the Prediction of Organic Chemistry Reactions	The use of neural networks for predicting reaction types	NNs for Prediction of Organic Chemistry Reactions
20	Expert System for Predicting Reaction Conditions: The Michael Reaction Case	Models were built to decide the compatibility of an organic chemistry process with each considered reaction condition option	Expert System for Predicting Reaction Conditions
21	Machine Learning in Chemical Reaction Space	Looked at reaction spaces of molecules involved in multiple reactions using ML-concepts	Machine Learning in Chemical Reaction Space
22	Machine Learning for Chemical Reactions	An overview of the questions that can and have been addressed using machine learning techniques	Machine Learning for Chemical Reactions
23	ByTorch overview	BoTorch as a framework of PyTorch	ByTorch overview
24	ByTorch official	Bayesian optimization or simply an official website of BoTorch	ByTorch official
25	VS Code Cheatsheet	VS Code Shortcut Cheatsheet	VS Code Cheatsheet
26	Simple Machine Learning Cheatsheet	The Machine Learning Cheatsheet of all fields making it and common used algorithms	Machine Learning Cheatsheet
27	DeepMind & UCL on Reinforcement Learning	DeepMind & UCL lectures as videos on Reinforcement Learning	DeepMind & UCL on Reinforcement Learning
28	Stanford Machine Learning Full Course	Full machine Learning course as lecture slides given at Stanford University	Stanford Machine Learning Full Course
29	Coursera's Deep Learning Specialization	DL Specialization given by teh great Andrew Ng and his team at deeplearning.ai	Coursera's Deep Learning Specialization
30	Simple Clustering Cheatsheet	Simple Unsupervised Learning Clustering Cheatsheet	Clustering Cheatsheet
31	Cheatsheet on Confusion Matrix	Cheatsheet on accuracy, precision, recall, TPR, FPR, specificity, sensitivity, ROC and all that stuff in Confusion matrix	Cheatsheet on Confusion Matrix
32	Cheatsheets for Data Scientists	Various and different cheatsheets for data scientists	Cheatsheets for Data Scientists
33	K-Means Clustering visualisation	Simple graphics explaining K-Means Clustering	K-Means Clustering visualisation
34	Youtube channel by 3Blue1Brown	Youtube channel on animated math concepts	Animated math concepts
35	Essence of Linear Algebra	Youtube playlist on Linear Algebra by 3Blue1Brown	Linear Algebra
36	The Neuroscience of Reinforcment Learning	The Princeton slides of Neuroscience for Reinforcement Learning	The Neuroscience of Rein forcement Learning
37	Reinforcement Learning of Drug Design	Reinforcement Learning implementation of Drug Design	Reinforcment Learning of Drug Design
38	Brain-Computer Interface with backing	Advanced BCI with a flexible and moldable backing and penetrating microneedles	Brain-Computer Interface with backing
39	Big O Notation	Great and simple explanation on Big O notation	Big O Notation
40	6 Data Science Certificates	6 Data Science Certificates to boost your career	6 Data Science Certificates
41	On the Measure of Intelligence	The new concept to measure how human-like artificial intelligence is	On the Measure of Intelligence
42	A Collection of Definitions of Intelligence	70-odd definitions of intelligence	A Collection of Definitions of Intelligence
43	Competition-Level Code Generation with AlphaCode	AlphaCode paper	Competition-Level Code Generation with AlphaCode
44	Machine Learning	What is Machine Learning? A well explained introdution	Machine Learning
45	Autoencoders	Introduction to Autoencoders and dive into Undercomplete Autoencoders	Autoencoders
46	ChatGPT Cheatsheet	A must-have Cheatsheet for anyone that is using ChatGPT a lot	ChatGPT Cheatsheet
47	Scikit-learn Cheatsheet	Scikit-Learn Cheatsheet fo Machine Learning	Scikit-Learn Cheatsheet
48	Top 13 Python Deep Learning Libraries	Summary of top libraries in Deep learning using Python	Top 13 Python Deep Learning Libraries
49	A Simple Guide to Machine Learning Visualisations	Summary of visual inspection on ML models performance	A Simple Guide to Machine Learning Visualisations
50	Discovering the systematic errors made by machine learning models	Summary to discover errors on Machine Learning models that achieve high overall accuracy on coherent slices of validation data	Discovering the systematic errors made by machine learning models
51	Hypothesis Testing Explaine?	Explanation of Hypothesis Testing	A Simple Guide to Machine Learning Visualisations
52	Intro Course to AI	Free introductory AI course for beginner's given by Microsoft	Intro Course to AI
53	ChatGPT productivity hacks	ChatGPT productivity hacks: Five ways to use chatbots to make your life easier	ChatGPT productivity hacks
54	Triple Money with Data Science	Article on how a fellow tripled his income with Data Science in 18 Months	Triple Money with Data Science
55	Predictions on AI for the next 10 years	Andrew Ng's prediction on AI for the next 10 years	Predictions on AI for the next 10 years
56	Theory of Mind May Have Spontaneously Emerged in Large Language Models	Publication overviewing LLM models like ChatGPT	Theory of Mind May Have Spontaneously Emerged in Large Language Models
57	How ChatGPT Helps You To Automate Machine Learning?	ChatGPT in Machine Learning	How ChatGPT Helps You To Automate Machine Learning?
58	The ChatGPT Cheat Sheet	Un-official ChatGPT cheat sheet	The ChatGPT Cheat Sheet
59	OpenAI Cookbook	Official ChatGPT cheat sheet	OpenAI Cookbook
60	Knowledge-augmented Graph Machine Learning for Drug Discovery: A Survey from Precision to Interpretability	Graph Machine Learning implementation in Drug Discovery	Knowledge-augmented Graph Machine Learning for Drug Discovery: A Survey from Precision to Interpretability
61	A Simple Guide to Machine Learning Visualisations	Guide to ML visualisations	A Simple Guide to Machine Learning Visualisations
62	How to Visualize PyTorch Neural Networks – 3 Examples in Python	3 examples of PyTorch visualisations	How to Visualize PyTorch Neural Networks – 3 Examples in Python
63	Role of Data Visualization in Machine Learning	Role of visualisation in ML	Role of Data Visualization in Machine Learning
64	Interpreting A/B test results: false positives and statistical significance	Interpretation of A/B test results	Interpreting A/B test results: false positives and statistical significance
65	Complete Guide to A/B Testing Design, Implementation and Pitfalls	Complete Guide to A/B Testing	Complete Guide to A/B Testing Design, Implementation and Pitfalls
66	Tips for Data Scienists and DataEngineers in their interviews	Tips for interviews by Seattle Data Guy	Tips for Data Scienists and DataEngineers in their interviews
67	Git Cheat Sheet for Data Science	Cheat Sheet of Git commands for Data Science	Git Cheat Sheet for Data Science
68	CNN for Breast Cancer Classification	Overview of an algorithm to automatically identify whether a patient is suffering from breast cancer or not by looking at biopsy images	CNN for Breast Cancer Classification
69	Goodhart’s Law	Overview of Goodhart’s Law used at OpenAI	Goodhart’s Law
70	How to Build an ML Platform from Scratch	Standard way to design, train and deploy model	directly How to Build an ML Platform from Scratch
71	Recap of Self-Supervised Learning	Overview of Self-Supervised Learning	Recap of Self-Supervised learning
72	Recap of MLOps (2021)	Overview of MLOps	Recap of MLOps (2021)
73	Recap of MLOps (2020)	Overview of MLOps	Recap of MLOps (2020)
74	Art of Neural Networks	Artistic representations of Neural Networks	Art of Neural Networks
75	Design patterns of MLOps	A summary of design patterns in MLOps	Design patterns of MLOps
76	How to Stay on Top of What’s Going on in the AI World	Resources on how to keep up with all the news and navigate through the endless stream of AI information	How to Stay on Top of What’s Going on in the AI World
77	ChatGPT and Whisper API	Integration tool for developer of ChatGPT and Whisper API	ChatGPT and Whisper API
78	20 Machine Learning Projects That Will Get You Hired	Projects thta should get you hired as an ML Engineer	20 Machine Learning Projects That Will Get You Hired
79	7 Top Machine Learning Programming Languages	Top programming languages used in Machine learning	7 Top Machine Learning Programming Languages
80	Effective Testing for Machine Learning Projects (Part I)	Blog post on Effective Testing for ML projects (Part I)	Effective Testing for Machine Learning Projects (Part I)
81	Effective Testing for Machine Learning Projects (Part II)	Blog post on Effective Testing for ML projects (Part II)	Effective Testing for Machine Learning Projects (Part III)
82	Effective Testing for Machine Learning Projects (Part III)	Blog post on Effective Testing for ML projects (Part III)	Effective Testing for Machine Learning Projects (Part III)
83	Decision making at Netflix	How Netflix uses A/B tests to make decisions that continuously improve their products, so they can deliver more joy and satisfaction to members	Decision making at Netflix
84	What is an A/B Test?	How Netflix uses A/B tests to inform decisions and continuously innovate on their products	What is an A/B Test?
85	Interpreting A/B test results: false positives and statistical significance	Interpreting A/B test results by looking at false positives and statistical significance	Interpreting A/B test results: false positives and statistical significance
86	Complete Guide to A/B Testing Design, Implementation and Pitfalls	End-to-end A/B testing for your Data Science experiments for non-technical and technical specialists with examples and Python implementation	Complete Guide to A/B Testing Design, Implementation and Pitfalls.
87	10 Statistical Concepts You Should Know For Data Science Interviews	Statistical Concepts necessary to be known for Data Science interviews	10 Statistical Concepts You Should Know For Data Science Interviews.
88	Evaluating Deep Learning Models: The Confusion Matrix, Accuracy, Precision, and Recall	Overview of evaluating ML models with metrics of Confusion Matrix, Accuracy, Precision, and Recall	Evaluating Deep Learning Models: The Confusion Matrix, Accuracy, Precision, and Recall
89	Artificial intelligence in medicine: Overcoming or recapitulating structural challenges to improving patient care?	Perspective of AI in Medicine	Artificial intelligence in medicine: Overcoming or recapitulating structural challenges to improving patient care?
90	Graph Neural Network in Drug Discovery	Deep Learning application to transform Drug Discovery process to increase the efficiency in finding new compounds	Graph Neural Network in Drug Discovery
91	New AI approach to reduce noise in X-ray data	Overview of the usage of autoencoders to replace noisy X-ray data with noise-free input signals	New AI approach to reduce noise in X-ray data
92	Natural Language Processing	The guide covers how it works, where it is applied top technques and more	Natural Language Processing
93	Big O Cheatsheet	Big O Cheatsheet for Data Structures #1	Big O Cheatsheet
94	Big O Cheatsheet	Big O Cheatsheet for Data Structures #2	Big O Cheatsheet
95	A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT	A historical overview of generative AI techniques and applications	A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT
96	ChatDoctor	A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain Knowledge	ChatDoctor
97	ALL CHEAT SHEET	Cheatsheets from Artificial Intelligence to Data Engineering to Machine Learning to Linux to Mathematics to R to Matlab and many more fields	ALL CHEAT SHEET

Worthy Repositories

(Back to top)

Worthy GitHub repositories related to the ML/DL/NN/AGI courses with all details included can be found here:

Number	Title	Description	Link
1	Advanced AI course	Code Academy Advanced AI course in Lithuania	Advanced AI course
2	GitHub on Coursera's Deep Learning Course	GitHub Repo for Coursera's Deep Learning Specialization by deeplearning.ai	GitHub on Coursera's DL Course
3	Notes on Coursera's Deep Learning Course	Lecture Notes for Coursera's Deep Learning Specialization by deeplearning.ai	Notes on Cousera's DL Course
4	Category Theory on Machine Learning	Github containing list of publications of Category Theory in various AI fields	Category Theory on ML
5	Foundations of Machine Learning	Understand the Concepts, Techniques and Mathematical Frameworks Used by Experts in Machine Learning	Foundations of ML
6	Awesome RL	Github repository on amazing materials on Reinforcement Learning	Awesome RL
7	Optimizing Chemical Reactions	Optimizing Chemical Reactions with Deep Reinforcement Learning	Optimizing Chemical Reactions
8	Machine Learning cheatsheets	Machine Learning cheatsheets on Supervised, Unsupervised & Deep Learning as well as Tips and Tricks	Machine Learning cheatsheets
9	ML Youtube Courses	Most recent Machine Leaning courses available on Youtube	ML Youtube Course
10	Machine Learning Course Notes	Notes on the courses related to Machine Learning	Machine Learning Course Notes
11	Effective Testing for ML Projects	GitHub repository for Effective Testing for ML Projects	Effective Testing for ML Projects
12	ChatDoctor	GitHub repository for ChatDoctor while it is written about it on 90th day or accessed as 96 item on tool	ChatDoctor GitHub
13	Auto-GPT	GitHub repository of an experimetal application showcasing the capabilites of GPt4	Auto-GPT
14	Vicuna-13B	An open-source chatbot trained by fine-tuning LLaMA on ~70K user-shared ChatGPT conversations	Vicuna-13B
15	Prompt Engineering Guide	Prompt Engineering Guide	Prompt Engineering Guide
16	Best-of Machine Learning with Python	910 curated ML projects	Best-of Machine Learning with Python
17	Data Science for Beginners - A Curriculum	Azure Cloud Advocates at Microsoft are pleased to offer a 10-week, 20-lesson curriculum all about Data Science	Data Science for Beginners - A Curriculum
18	Data-Science-Interview-Resources	Data Science Interview Resources	Data-Science-Interview-Resources
19	AWESOME DATA SCIENCE	Open source Data Science repository to learn and apply data science skills towards solving real world problems	AWESOME DATA SCIENCE

Notebooks

(Back to top)

Done notebooks of various datasets can be found here.

Notes

(Back to top)

Additional notes that we covered through lectures or additional material that I said about can be found here.

100DaysOfMLCode

(Back to top)

This is the section of 100DaysOfMLCode challenge updated daily by adding what has been done each day.

Machine Learning Regression Notebook | Day 1

• Check out the Jupyter code for Regression here.

Machine Learning Classification Notebook | Day 2

• Check out the Jupyter code for Classification here.

Data Preprocessing and Beneficial Website | Day 3

• Check out the code snippet for Data Preprocessing here.

• Added beneficial website as item 3 of public open-source datasets for AI here.

Simple Linear Regression Info and Beneficial Websites | Day 4

• Check out the code snippet for Simple Linear Regression here.

• Added beneficial websites as items 2 & 3 of Deep Learning Course & its lecture notes here.

Multiple Linear Regression and ML Cheatsheet | Day 5

• Check out the code snippet for Multiple Linear Regression here.
• Added a huge Cheatsheet on Machine Learning as item 4 here via GitHub repo containing classical equations with diagrams that helped recall knowledge and ideas on Machine Learning.

Universal Intelligence and K Nearest Neighbours | Day 6

• Added a publication (5) on Universal Intelligence: A Definition of Machine Intelligence here that looks into informal definitions of intelligence defined by experts, then mathematically investigates what is intelligence for machines and studies other tests and definitions of intelligence proposed for machines.
• Learnt about K Nearest Neighbours algorithm and made a graphical summary below as well as here.

KNN code, Notebook on TF Tensors, Creativity of ChatGPT & AI Art | Day 7

• Wrote about the K Nearest Neighbours algorithm for classification as a code snippet that can be found here and honed expertise of Deep Learning framework TensorFlow by making a notebook that looked into TensorFlow tensors here.
• Read articles on how to improve creative writing through ChatGPT here where I loved the poem about Python after trying it myself that left me certain that ChatGPT could be a good collaborator on creative writing and on the potential of AI in the art here that may lead to the future of social activism.

Algorithms, Category Theory in ML & ML experiment tracking | Day 8

• Finished 'Grokking Algorithms: An illustrated guide for programmers and other curious people' by Aditya Y. Bhargava that can be found as item 1 here. Recommend it highly as algorithms are explained simply through visualisations and some usage of algorithms in ML is visualised as well. Loved it. Also found another technical book of Steven Skiena's 'Algorithm Design Manual' by reading its preface that will help to hone expertise on algorithms further as it can be found as item 2 here with videos that complement the book here.

• Began diving into Category Theory and its usage in Machine Learning. A nice GitHub repository that lists all of the relevant papers which can be found as item 4 here while to get a good grasp of Category Theory started reading the book of Category Theory for Programmers by Bartosz Milewski here as also it can be inspected through here as item 3 where a blog on which the book is based is given.

• Dived into ML experiment tracking here that in a few words is the process of saving all the experiment related information.

Automated ML, Algorithm Design Manual & Logistic Regression | Day 9

• To work out how we could automate all aspects of ML and data analysis pipeline found this awesome book as item 4 here. I highly recommend it to any machine learning researcher wanting to get started in the field and to any practitioner looking to understand the methods behind all the AutoML tools out there. Do check it out. After finishing with the current technical book that is going to be my the third technical book of the year to go hand in hand with this one.

• Started reading 'Algorithm Design Manual' to refresh as well as strengthen knowledge on algorithms used in Machine Learning and Computer Science as full book can be found as item 2 here with videos that complement the book here.

• To clear my insights on Logistic Regression I was searching on the internet for some well documented sources and came across the article as item 6 here. It provides a detailed description of Logistic Regression and I recommend to check it out.

Support Vector Machines & Brain-Computer Interface | Day 10

• Strengthened understanding on what Support Vector Machine is, how it is used to solve classification problems and honed expertise about its usage.
• Made a graphical summary of SVM below as well as here.
• Looked at Brain-Computer Interface (BCI) as a good summary is given as item 7 here and a nice article on research fascinating news as item 8 here

Code on SVM & AI in Chemistry| Day 11

• Implemented Support Vector Machine (SVM) on linearly related data while using Scikit-Learn. As in this library we have SVC classifier I used it to solve the task. The code snippet of it can be found here.
• Coming from chemical background made me hyper excited to study about ML influence on Chemistry through diving into it while reading a number of articles of which some highlights could be 9, 10, 11 & 12 as found here.

Notebooks on PyTorch Tensors & Visualisations | Day 12

• Made two Jupyter notebooks. One with simple analysis of PyTorch Tensors as found here and the other on visualising Neural Networks through Pytorch here.

Perceptron with PyTorch, Naive Bayes Classifier & Black Box ML | Day 13

• Made a notebook with a simple overview of Perceptron theory and its usage through PyTorch as found here.
• Learned about different types of naive bayes classifiers. Also started to hone Machine Learning expertise by studying the lectures given by Bloomberg as found as item 5 here. First one in the playlist was Black Box Machine Learning. It gives the whole overview about prediction functions, feature extraction, learning algorithms, performance evaluation, cross-validation, sample bias, nonstationarity, overfitting, and hyperparameter tuning.

Decision Trees & Original first paper on AI with its analysis | Day 14

• Made a graphical summary of Decision Trees below as well as here.
• Read Alan Turing's original paper on the foundation of AI as found as 13 here or accessed through here and its analysis as item 14 here or accessed through here.

Code on Decision Trees & Paper contradicting 'Turing Test' with its analysis | Day 15

• Check out the code snippet for Decision Trees here.
• Read John R. Searle's paper contradicting 'Turing Test' as item 15 here with its analysis as found as 16 here.

Neural Networks & Its Architectures | Day 16

• An amazing video on Neural Networks by 3Blue1Brown youtube channel. This video gives a good understanding of Neural Networks and uses Handwritten digit dataset to explain the concept. Link to the video found as item 17 here or accessed through here.

• A great article going though Neural Network 8 architectures that every ML engineer needs to know found as it 18 here or accessed through here.

Machine Learning in Chemistry | Day 17

Read about Machine Learning concepts in Chemistry and particularly in automating and predicting chemical reactions as well as other chemical niceties:

1. Most cited article is on the reaction predictions for organic chemistry where these reactions were explored by the use of neural networks. This newly developed predictor built a system which predicts the likely products of these reaction. Further details found as item 19 here or accessed though here.
2. Machine Learning methods (Support Vector Machine, Naive Bayes, and Random Forest) looked at the compatibility of specific chemical processes and the feasability of these predicted reactions. The link as item 20 found here or accessed though here
3. Machine Learning studied one of the largest reaction space to date by creating a database that contains all possible chemical reactions found as item 21 here or accessed though here
4. The review overviewed how important chemical questions that could be answered through using machine learning techniques as found as item 22 here or accessed though here

Image Recognition | Day 18

• Made a Notebook implementing deep neural networks on image recognition with PyTorch as found here.

Fuel Efficiency | Day 19

• Made a Notebook implementing linear regression with deep neural networks to predict Miles Per Gallon (MPG) values on fuel efficiency across the US, Europe and Japan as found here.

BoTorch & Reinforcement Learning | Day 20

• Studied about BoTorch as a low level framework of PyTorch which introduction can be found as item 23 here or accessed through here or full Bayesian optimization as it says as found as item 24 here or accessed through here.

• Found VS code shortcut cheatsheet as found as item 25 here or accessed through here.

• Came across an awesome Reinforcement Learning material that includes everything from codes to theory to Lectures, Papers to Applications and other amazing material on RL you can check by visiting item 6 here that can also be accessed straight from here.

TensorFlow Eager with Graph Executions & Simple ML Cheatsheet | Day 21

• Wrote a notebook by comparing Eager and Graph executions in TensorFlow here
• Analysed a simple, short and to the point Machine Learning cheatsheet that can be found as item 26 here or accessed straight through here.

DeepMind/UCL Lectures & ML and DL courses & Simple Clustering Cheatsheet | Day 22

• Honed knowledge of Reinforcment Learning through studying DeepMind and UCL lecture slides on it as item 27 here or accessed through here.

• Found a fantastic full course on Machine Learning by the great Andrew Ng as item 28 here or accessed through here and two years ago did this on as item 29 found here or accessed through here which I also highly recommend to begin learning about Deep Learning as time from time I revisit it that I did today for example.

• Analysed a short cheatsheet on Clustering and added it as item 30 here or accessed through here.

Random Forest & Confusion matrix Cheatsheet | Day 23

• Made a graphical summary of Random Forest below as well as here.

• Found a fantastic cheatsheet on Confusion Matrix that incorporates accuracy, precision, recall, TPR, FPR, specificity, sensitivity, ROC and added it as item 31 here or accessed through here.

Code on Random Forest & Cheatsheets for Data Scientists | Day 24

• Check out the code snippet for Decision Trees here.

• Found various cheatsheets for Data Scientists as item 32 here or accessed through here as the glimpse given below.

K-Means Clustering | Day 25

• Strengthened knowledge about Unsupervised Learning and particularly Clustering by creating a visual on K-Means as shown below and found a wonderful animation that can help to easily understand K-Means Clustering as found as item 33 here or accessed through here.

Linear Algebra | Day 26

• Found an awesome channel as item 34 here or you can check the channel directly here by 3Blue1Brown. It has a playlist called Essence of Linear Algebra. Started yesterday and completed full playlist of videos today which gave a complete overview of Vectors, Linear Combinations, Spans, Basis Vectors, Linear Transformations, Matrix Multiplication, 3D Transformations, Determinants, Inverse Matrix, Column Space, Null Space, Non-Square Matrices, Dot Product, Cross Product, Eigenvectors, Eigenvalues and Abstract Vector Spaces.

• Link to the playlist of Essence of Linear Algebra can be found as item 35 [here] or accessed straight through here.

Reinforcement Learning | 27

• Found an amazing Princeton material as slides on the Neuroscience of Reinforcement Learning as item 36 here or accessed straight through here. Looked also at overview of Reinforcement Learning implementation for Drug Design as found as item 37 here or accessed through here.

Employee Performance with PyCaret | Day 28

• Made a Notebook implementing regression with Pycaret to look at employee performance here.

BCI, Chemical Reactions & Big O | Day 29

• Found a great article on Brain-Computer Interface as item 38 here where it speaks about closed-loop system possibility once penetrating microneedles can conform to the brain or simply about an advanced brain-computer interface with a flexible and moldable penetrating microneedles that gets to the brain's cortex. It can also be accessed through here.
• Came across a GitHub repository on optimizing chemical reactions through Reinforcement Learning as item 7 here or accessed through here.
• Also found a fantastic explanation on Big O notation as item 39 here or accessed through here.

DS Certificates, Chemical Reactions & Big O | Day 30

• Came across 6 Data Science certificates in one place that could boost your career as found as item 40 here or accessed through here. Particularly interested in Google Professional Data Engineer Certification & SAS Certified AI & Machine Learning Professional. Take a look youself. Maybe you will find something useful as well.
• Also found GitHub repo of Machine Learning cheatsheets on Supervised, Unsupervised & Deep Learning as well as Tips and Tricks given by Stanford CS course. Details as item 41 here or accessesd through here.

Mathematics for CS and ML | Day 31

• Started reading lecture notes as books of MIT and University Of California on Mathematics for Computer Science and Mathematics for Machine Learning as items 5 and 6 here and here or accessed through here and here.

Quizzes about TensorFlow & PyTorch | Day 32

• Made two quizzes about TensorFlow and PyTorch combining 25 questions each. Quiz on TensorFlow can be found here while on PyTorch can be found here.

PyCaret, PyTorch & Applied Artificial Intelligence | Day 33

• Created problems for PyCaret and PyTorch as found here and here. Their solutions could be also found here and here.
• Found an AI book on engineering Artificial Intelligence applications as item 7 here or accessed through here.

DL with Python, TensorFlow, Keras & Encoding | Day 34

• Watched Youtube videos to replenish knowledge on Deep Learning with Python, TensorFlow and Keras through four recordings:

1. Deep Learning with Python, TensorFlow, and Keras tutorial
2. Loading in your own data
3. Convolutional Neural Networks
4. Analyzing Models with TensorBoard

• Made a notebook looking at Ordinal and One Hot Encodings as found here.

Essential Papers, AlphaCode & ML | Day 35

• Read three papers as items 41, 42 and 43 as found here or summarrised and accessed below:

1. On the Measure of Intelligence that explained the new concept of how to measure human-like artificial intelligence that enables fair general intelligence comparisons between AI systems and humans. Written by creator of Keras, Francois Chollet.
2. A Collection of Definitions of Intelligence that looked at 70-odd definitions of intelligence.
3. Competition-Level Code Generation with AlphaCode that looked into the AlphaCode, a system for code generation that can create novel solutions to competitive programming problems that require deeper reasoning like knowing many computer science algorithms to implement. Fantastic read.

• Found an awesome quick explanation about Machine Learning as item 44 found here or accessed through here. It explained what Machine Learning is, how it works, and its importance in five minutes of reading.

Power of DL & Scientific Discovery with AI | Day 36

• Watched an awesome video from DeepMind on the Power of Deep Learning that can be accessed through here.
• Also watched another video from the creator of DeepMind, Demis Hassabis, on the usage of AI to accelerate scientific discovery as found here.

Automate ML pipeline & Autoencoders | Day 37

• Read the short book of automating Machine Learning pipeline as item 8 here or accessed through here. This short overview looked at the lifecycle using the Databricks Lakehouse Platform.
• Studied Autoencoders that give a good representation of your data that focuses on the signal rather the noise. Found and article that briefly introduced Autoencoders and dived deeper into an Undercomplete Autoencoder, suitable for dimensionality reduction and feature extraction as item 45 here or accessed through here.

Machine Learning Yearning | Day 38

• Came across a Machine Learning Yearning book as item 9 here that is suited for AI Engineers in the era of Deep Learning where it answers such queries as techniques for reducing avoidable bias, deciding whether to include inconsistent data, generalizing from the training set to the dev set, identifying Bias, Variance, and Data Mismatch Errors as well as spotting a flawed ML pipeline to name a few of the questions that the book answers. It can also be accessed straight through here.

ChatGPT & Scikit-learn Cheatsheets | Day 39

• Found an awesome Cheatsheet regarding ChatGPT usage. As OpenAI said it's a must-have for anyone looking to get the most out of ChatGPT or NLP tasks in general. It can be found as item 46 here or accessed directly through here with KDnuggets post on it here.
• Also came across a cheatsheet of Scikit-learn on Machine Learning that can be found as item 47 here or accessed straight by clicking on here with KDnuggets post on it here. A bit on Scikit-learn: Scikit-learn is an open-source Python library for all kinds of predictive data analysis. You can perform classification, regression, clustering, dimensionality reduction, model tuning, and data preprocessing tasks.

ML Videos, Top 13 & ML Courses | Day 40

• Came across a fantastic GitHub repository that gives useful ML courses on the Youtube videos where you could refresh yor Machine Learning expertise ranging from Deep Learning to Reinforcement Learning to Graph Machine Learning asnd other subcategories through watching them as found as item 9 here or accessed straight through here.
• Found Top 13 Deep Learning libraries summarised in one article found as item 48 here or accessed straight through here.
• Stumbled across another fantastic GitHub repository on Machine Learning Courses but this time it provides notes on the
  courses like for Deep Learning Specialization of 2022 or MIT's Introduction of Deep Learning to name a few. It can be accessed as item 10 here or through this link directly.

Visualisations, Errors & Testing | Day 41

• Took today a bit easier and spent time reading articles. The ones I found interesting are items 49, 50 and 51 where a simple guide of vislisations on Machine Learning is given, then a blog post that helps discovering errors in your Machine Learning models and lastly a well explained overview on Hypothesis Tedting. These article coulds be found here or accessed directly through here:

1. A Simple Guide to Machine Learning Visualisations
2. Discovering the systematic errors made by machine learning models|
3. Hypothesis Testing Explained

AI Course, ChatGPT hack & Money | Day 42

• Found a well balanced beginners course on AI by Microsoft as item 52 here or accessed directly through here.
• Also spent time reading articles and the two ones I found interesting give ChatGPT productivity hacks and explanation on how to triple your income with Data Science as items 53 ant 54 here or accessed directly through here:

1. ChatGPT productivity hacks
2. Triple Money with Data Science

Neural Nets on Tabular Data | Day 43

• Took it easy today. Created two notebooks with some explanations on Neural Nets for Tabular Data there while using TensorFlow and PyTorch. The former uses in-built embeddings and is short and can be found here while the latter uses Neural Nets for Tabular Data with PyTorch with less explanation and can be found here.

• Came across predictions on AI by Andrew Ng for the next 10 years. Great read. Have a look yourself as item 55 here or access straight through here.

ChatGPT & Think Bayes | Day 44

• Delved into ChatGPT by reading a paper showing that it performs much better than GPT3 and more like a nine-year-old kid. It can be found as item 56 here or accessed straight through here and read a nice article on how ChatGPT helps to automate Machine Learning projects found as item 57 here or accesed straight through here.

• Came across a book on an introduction to Bayesian statistics as item 10 there or could be accessed straight here that uses computational methods relevant to ML practitioners:

  1. This book uses Python code instead of math!
  2. There’s a Jupyter notebook for every chapter
  3. Code is written in NumPy, SciPy, and Pandas

PyTorch Presentation | Day 45

• Created PyTorch presentation that can be accessed through here as a pdf or as a poweproint presentation while clicking here.

FastAI with Tabular Data | Day 46

• Created two notebooks looking at Tabular Data with FastAI. The first one is short and an overview of FastAI with tabular data that can be found here while the second notebook looked at entity embeddings of tabular data where embeddings could be understood as modified categorical variables where I compared Neural Nets with Random Forest as well as Ensemble machine and is available here.

Podcasts on AI, ML, CS & Analytics | Day 47

• Created a list of podcasts that I like to listen on Machine Learning, AI and DS from time to time. Here are the 10 most popular of them as such:

1. Data Skeptic | Features interviews and discussion of topics related to data science, statistics, machine learning, and artificial intelligence from the perspective of applying critical thinking and the scientific method to evaluate the veracity of claims and efficacy of approaches.
2. Data Stories | Discussions on the latest developments in data analytics, visualization, and related topics.
3. Lex Fridman Podcast | Conversations at MIT and beyond about the nature of intelligence and AI from the perspectives of deep learning, robotics, AGI, neuroscience, philosophy, psychology, cognitive science, economics, physics, and mathematics.
4. Linear Digressions | An exploration of machine learning and data science through interesting (and often very unusual) applications.
5. TWIMLAI | This Week in Machine Learning & AI caters to a highly targeted audience of machine learning and AI enthusiasts. Covering technologies such as machine learning, artificial intelligence, deep learning, natural language processing, neural networks, analytics, and deep learning.
6. SuperDataScience | Bringing you the most inspiring Data Scientists and Analysts from around the world to help you build your successful career in Data Science. Data is growing exponentially and so are salaries of those who work in analytics. This podcast can help you learn how to skyrocket your analytics career.
7. Talking Machines | Katherine Gorman and Neil Lawrence bring you clear conversations with experts in the field, insightful discussions of industry news, and useful answers to your questions. Machine learning is changing the questions we can ask of the world around us, here we explore how to ask the best questions and what to do with the answers.
8. The AI Podcast form NVIDIA | We connect with some of the world’s leading AI experts to explain how it works, how it’s evolving, and how it intersects with every facet of human endeavor. NVIDIA, the AI computing company, produces this podcast.
9. The Digital Analytics Power Hour from Michael Helbling, Tim Wilson, and Moe Kiss | Attend any conference, and you will hear people say that the most informative discussions happened in the bar after the show. Read any business magazine, and you will find an article saying something along the lines of "Business Analytics is the hottest job category out there, and there is a significant lack of people, process and best practice." In this case, the conference was eMetrics, the bar was… multiple, and the attendees were Michael Helbling, Tim Wilson, and Jim Cain (Co-host Emeritus). After a few pints and a few hours of discussion about the cutting edge of digital analytics, they realized they might have something to contribute back to the community. This podcast is one of those contributions. Each episode is a closed topic and an open forum - the goal is for listeners to enjoy listening to Michael, Tim, and Moe share their thoughts and experiences and hopefully take away something to try at work the next day.
10. AI in Business Podcast with Daniel Faggella | Learn what's possible - and what's working - with artificial intelligence in the enterprise through interviews with top AI and machine learning-focused executives and researchers in sectors like Pharma, Banking, Retail, and Defense. Discover trends, learn about what's working now, and learn how to adapt and thrive in an era of AI disruption.

• Also worth mention are these podcasts:
  • WiDS (Women in Data Science) | Data science is improving outcomes in a wide range of domains, from healthcare to seismology to human rights and more. Hear from women leaders across the data science profession, as they share their advice, career highlights, and lessons learned along the way.
  • Data Science Salon Podcast | Interviews with top and rising luminaries in data science, machine learning, and AI on the trends and business use cases that are propelling the field forward.
  • Voices in AI from GigaOm| Today's Leading Minds Talk AI with Host Byron Reese.
  • Machine Learning Guide | Teaches the high-level fundamentals of machine learning and artificial intelligence including basic intuition, algorithms, and math. With discussions on languages and frameworks and deep learning, each episode offers a high-quality curated resource for learning each episode’s details.
  • Freakonomics Radio | Discover the hidden side of everything with Stephen J. Dubner, co-author of the Freakonomics books. Each week, Freakonomics Radio tells you things you always thought you knew (but didn’t) and things you never thought you wanted to know (but do) — from the economics of sleep to how to become great at just about anything. Dubner speaks with Nobel laureates and provocateurs, intellectuals and entrepreneurs, and various other underachievers. Special features include series like “The Secret Life of a C.E.O.” as well as a live game show, “Tell Me Something I Don’t Know.”
  • Talk Python To Me | Covering a wide array of Python and related topics, our goal is to bring you the human story behind the Python packages and frameworks you know and love.

ChaGPT Cheat Sheets & Books | Day 48

• ChatGPT Cheat Sheets could be found as items 58 and 59 here where you could learn ChatGPT tips and tricks for NLP, Code, Structure and Unstructured output, Media types, and Meta ChatGPT and here for understanding OpenAI API and using it to build ChatGPT applications or accessed throuh here and here
• Books on ChatGPR as items 11, 12 and 13 could be found here where it provides 100 resources to enhance your life with ChatGPT, here where you could learn strategies for crafting compelling ChatGPT prompts that drive engaging and informative conversations and here to learn how to prompt for software engineering tasks or accessed through here, here and here.

Could AI revolutionise Drug Discovery? | Day 49

• Read article on Graph Machine Learning for Drug Discovery. As DL applciations have been on the rise in Drug Discoveryy yet Graph Machine Learning has gained considerable attention for its exceptional ability to model graph-structured biomedical data and investigate their properties and functional relationships. Details are found as item 60 here or accessed straight through here

Machine Learning Visualisations | Day 50

• Studied about Machine Learning Visualisations. Remembered the basics (1^st link), then studied the implementation in PyTorch that I use frequently (2^nd link) and finished by looking at visualisations role in ML (3^rd link.) These articles can be accesesed though here as there they are as items 61, 62 and 63 or by clicking on a link below:
  1. A Simple Guide to Machine Learning Visualisations
  2. How to Visualize PyTorch Neural Networks – 3 Examples in Python
  3. Role of Data Visualization in Machine Learning

Work in progress | Day 51

• Worked on the private repository of my own ML Project and dived into A/B testing by looking here or here as well as found tips for Data Scientists and Data Engineers in their interviews given by Seattle Data Guy here. All of the links can also be found here as items 64, 65 and 66.

ML Project & Git Cheat Sheet | Day 52

• Worked on the private repository of my own ML Project and came across a Cheat Sheet of Git commands for Data Science as could be acessed through a list here as item 67 or directly thourgh here. A summary of what it contains is described in this website by KDnuggets.

CNN for Breast Cancer & Goodhart’s Law | Day 53

• Found an article on Convolutional Neural Nets for Breast Cancer Classification that built an algorithm to automatically identify whether a patient is suffering from breast cancer or not by looking at biopsy images. The implementation could be found as item 68 here or accessed straight through here.
• Looked at Goodhart’s Law that says: “When a measure becomes a target, it ceases to be a good measure.”. This philosophy is strived for in OpenAI. More as item 69 here or accessed through here.

Free ML Courses & Building ML Platform | Day 54

• Came across well acknowledged Machine Leaning courses for free such as:
  • Top 5 free ML courses
  • Machine Learning Systems Design: A Free Stanford Course
  • Python for Data Science, AI & Development
• Continued working on my own ML Project as took notes from building an ML model from scratch as accessed as item 70 here or given directly here.

Self-Supervised Learning | Day 55

• Studied and dived into the world of Self-Supervised Learning as it could be accessed through item 71 here or directly through here. In short terms it is known as the dark matter of AI as it is a type of Unsupervised Learning and the list of the valuable articles on it are:
  1. A New Series About Self-Supervised Learning
  2. Self-Supervised Learning for Computer Vision
  3. Self-Supervised Learning for Speech
  4. Self-Supervised Learning for Language
  5. Self-Supervised Learning as Non-Contrastive Learning
  6. Self-Supervised Learning as Energy Based Methods
  7. How Contrastive Learning Influences Self-Supervised Learning methods

MLOps, ML in Medicine & Ethics of AI | Day 56

• Studied about MLOps where great recaps on it could be found as items 72 and 73 here or accessed directly through here and here.

• Read about Machine Learning applications in Medicine (Rheumatology) as could be found by accessing directly through here.

NN Art & More MLOps | Day 57

• Found artistic representations of neural networks as item 74 here or accessed directly through here.
• Dived more into MLOPs as its design patterns could be found as item 75 here or accessed directly through here.

Stay on top with AI world | Day 58

• Found the article of most rewarding resources to stay on top with fast moving AI world as item 76 here or accessed directyly through here. It includes Youtube channels worth following, Arxiv dataset with papers, Papers With Code on the newest ML research with repos, and of course Twitter posts on AI like following my created list where you culd get news on AI world (constantly updated when a new AI worthy account is included), Public Speaking, Investment, my posts and the fun that comes with all of that.

Geometric Deep Learning | Day 59

• Listened to an awesome lecture on never underestimating symmetry for Deep Learning as accessed directly though here.

PyTorch Notebook of Fundamentals | Day 60

• Created a notebook of PyTorch Fundamentals that looks into tensors, tensor operations like sum, subtraction, division, element-wise and particularly matrix multiplications in depth, then tensors usage between NumPy and PyTorch, indexing, reproducibility and the usage of GPU for speeding up tensor calculations to name a few of the things that are covered there. The notebook can be found here.

ChatGPT and Whisper API | Day 61

• Started using ChatGPT and Whisper API's to integrate its models in my ML projects. It was released recently by OpenAI for developers to improve their work as these API's could be found as item 77 here or accessed directly through here.

Top ML Projects $ DS Interviews | Day 62

• Came across a wonderful KDnuggets article of what should get you hired as an ML Engineer when completing one of the projects like MNIST Digit Classification, Heart Disease Prediction or Sales Forecasting to name a few of the 20 offered as the rest could be found as item 78 here or accessed directly through here.
• Every one knows that for Machine Learning you need to master Python, however there are other programming languages that could boost your arsenal in ML as well. Such could be Java and Javascript while the rest are found as top 7 ML pragramming languaes as item 79 here or accessed directly through here.

Effective Testing for ML Projects | Day 63

• Found a wonderful blog that summarises the effective testing for Machine Learning Projects by giving and solving examples. The blog posts could be found as items 80, 81 and 82 here or accessed directly through here, here and here. The GitHub repository of the project could be found also as item 11 here.

A/B Testing | Day 64

• Studied about A/B Testing while understanding its fundamentals, working through Python examples and digging into False Negatives and False Positives as more on that could be found as items 83 84, 85 and 86 here or accessed directly through here, here, here and here.

Statistical Concepts in Data Science | Day 65

• Refreshed knowledge about statistical concepts necessary to be known for Data Science interviews ranging from Z-tests and T-tests to Uniform and Poisson Distributions to name a few ot the 10 that could be found as item 87 here or accessed directly through here.

Python Tricks & Reinforcement Learning | Day 66

• Came across two books of Python Tricks and an overview on Reinforcement Learning:
  1. Python Tricks: The Book — A buffet of Awesome Python Features can be found here.
  2. Slides, Solutions and Codes about introduction on Reinforcement Learning from fundamentals to advanced topics here while the book here.

To get either of the books for free if unavailable through links head and search the name through this awesome website.

SQL: Videos, Cheat Sheets, Interviews & Articles | Day 67

• Refreshed expertise by watching, founding cheat sheets, reading prepartions for interview questions as well as other articles on SQL as worthy 13 of them are given below:

1. Funny Video - SQL Interviews Be Like
2. Video Tutorial - SQL Tutorial - Full Database Course for Beginners
3. Video Tutorial - Learn SQL in 1 Hour - SQL Basics for Beginners
4. Video Tutorial - SQL Full Course | SQL Tutorial For Beginners | Learn SQL
5. Video - How To Write Better SQL In 7 Minutes
6. Cheat Sheet - SQL Notes for Proffesionals
7. Cheat Sheet - Data Preparation with SQL Cheatsheet
8. Course - Free SQL and Database Course
9. Interview - 24 SQL Questions You Might See on Your Next Interview
10. Interview - Uber SQL Interview Answers
11. Interview - 3 SQL Interview Tips And Questions For Data Scientists And Data Engineers
12. Article - How to Get Up and Running with SQL – A List of Free Learning Resources
13. Article - Handling Missing Values in Time-series with SQL

Pandas for Data Science | Day 68

• Put together insightful Pandas learning resources for Data Science. Some need to be subscribed/paid but it is worth it as they are a joy to the eyes. These include courses/tutorials for using Pandas to explore datasets, dataframes, sort, clean, read and write data as well as some its tricks to name a few of the sources. There is a total of 13 learning resources as found below:

1. Course - Explore Your Dataset With Pandas - 47 minutes
2. Course - The Pandas DataFrame: Working With Data Efficiently - 130 minutes
3. Course - Sorting Data in Python With Pandas - 26 minutes
4. Course - Data Cleaning With pandas and NumPy - 88 minutes
5. Course - Reading and Writing Files With Pandas - 49 minutes
6. Course - Plot With Pandas: Python Data Visualization Basics - 28 minutes
7. Course - Combining Data in pandas With concat() and merge() - 94 minutes
8. Course - Idiomatic Pandas: Tricks & Features You May Not Know - 47 minutes
9. Course - Using Pandas to Make a Gradebook in Python - 97 minutes
10. Tutorial - SettingWithCopyWarning in pandas: Views vs Copies
11. Tutorial - Fast, Flexible, Easy and Intuitive: How to Speed Up Your pandas Projects
12. Tutorial - pandas GroupBy: Your Guide to Grouping Data in Python
13. Tutorial - NumPy, SciPy, and pandas: Correlation With Python

Machine Learning Blogs | Day 69

• Assembled a list of Machine Learning Research Blogs to follow with simple overviews what each provides. The list is as follows:
  • Machine Learning, Towards AI - Aims to publish unbiased machine learning related articles and be an impartial source of information.
  • Amazon Science Blog - Scientific blog that encompasses work from Amazon’s science community, and its research areas include cloud and systems, computer vision, conversational AI, NLP, machine learning, robotics, search and information retrieval and security, privacy, and abuse prevention.
  • Machine Learning Blog, ML@CMU, Carnegie Mellon University - General-audience medium for researchers to communicate research findings, perspectives on the field of machine learning, and various updates.
  • Distill - The distinguishing trait of a Distill article is outstanding communication and a dedication to human understanding. Distill articles often, but not always, use interactive media.
  • Google AI Blog - Google AI conducts research that advances the state-of-the-art in the field and the Google AI blog has a section specifically for machine learning research.
  • Data Science Dojo - An education startup that enables professionals to extract actionable insights from data. They have an exciting machine learning blog, which has several very informative articles on machine learning.
  • Neptune.AI - Remarkable machine learning blog, offering tutorials on machine learning modeling, hyperparameter optimization, model evaluation, data exploration, generative models, machine learning tools, and many more. Neptune.AI also offers a framework that makes it easier to track versions of your Jupyter notebooks, helps with managing your experimentation process, and integrates with your team’s workflow easily.
  • BAIR Berkeley - The BAIR blog provides an accessible, general-audience medium for researchers to communicate research findings, perspectives on the field, and various updates. Posts are from students, postdocs, and faculty in BAIR and intend to provide a relevant and timely discussion of research findings and results, both to experts and the general audience.
  • OpenAI - The OpenAI blog brings state-of-the-art research in the field. Their mission is to discover and enact the path to safe artificial general intelligence (AGI).
  • Machine Learning (Theory) by John Langford - The Machine Learning (Theory) blog is an experiment in the application of a blog to academic research in machine learning and learning theory by machine learning researcher John Langford. He has emphasized that the field of machine learning “is shifting from an academic discipline to an industrial tool”.
  • DeepMind Blog - DeepMind works on some of the most complex and exciting challenges in AI. Their world-class research has resulted in hundreds of peer-reviewed papers, including in Nature and Science.
  • Machine Learning at MIT - MIT often produces state-of-the-art research in the field of machine learning. This filtered news stream provides the latest news and research on what is happening in the field of machine learning at MIT.
  • Colah’s Blog - Christopher Olah describes himself as a wandering machine learning researcher, looking to understand things clearly and explain them well. Olah is a researcher with Open AI and formerly at Google AI. His blog has complete and exciting articles for the machine learning researcher and enthusiast — a gold mine of free, open, machine learning research.
  • Facebook's AI Blog - Facebook AI is known for working on state-of-the-art research in the field. Their research areas focus on computer vision, conversational AI, integrity, NLP, ranking and recommendations, systems research, machine learning theory, speech, and audio, along with human and machine intelligence. The Facebook AI Blog encompasses excellent content, from blog posts to research publications.
  • Amazon AWS Machine Learning Blog - Amazon web services (AWS) is one of the most used cloud services around the world. They offer reliable, scalable, and accessible cloud computing services. Their research team publishes blog posts on machine learning state-of-the-art research and ML applications on this AWS blog.

Metrics in ML & Python Goodies | Day 70

• Found a fantastic overview on evaluating ML models through metrics of Confusion Matrix, Accuracy, Precision, and Recall as item 88 here or accessed directly through here.
• Great visual summary of Python libraries and frameworks ranging from Machine Learning to Image Processing to Automation Testing to Web Development to Game Development to Web Scraping shown below.

Artificial Intelligence in Medicine | Day 71

• Read a great perspective of AI in Medicine found as item 89 here or accessed directly through here. To sum up the article it speaks that the ambitions driving enthusiasm about AI in Medicine include the goals/challenges of promoting decisions that are informed by a comprehensive assessment of available data, ensuring that the relative merits of policies, practices, procedures and interventions are clearly assessed before they are implemented in practice and continuously monitoring clinical workflows and practice patterns so that they can be adjusted in light of changing circumstances. It declares that applications of AI are likely to play a valuable role in advancing each of these goals/challenges.

MoLeR - GNN in Drug Discovery | Day 72

• Found a great Graph Neural Network application, MoLeR, in efficient drug discovery to help transform the process and enable to increase the efficiency in finding new compounds. MoLeR not only needs fewer steps to construct drug-like molecules, but its generation procedure also occurs in steps that are more akin to the way chemists think about the construction of molecules. More on it as item 90 here or accessed directly through here.

AI still needs humans | Day 73

• While reading articles on AI wear realised that with the growing capabilities and outsource of AI across a lot fields one needs to think of AI as simply taking care of a grass. If you do not cut it will become overgrown and messy. Same for AI: we need to make constant reviews to reduce AI biases, take care for changes that could weaken our data models and most importantly take care for our models daily to support our companies' future successes. It is worth noting that:
  • Just like physical tools such as laptops, allocate budget for AI wear and tear. Set aside funds in your company's annual spending forecasts for AI repairs and improvements, to ensure your business stays competitive with industry standards.
  • And a workforce that co-exists with AI breeds a stronger support system and more succesful environment where each can strive, with more people ready to spot issues and improvements and use artificial intelligence to its full potential. After all, returning to my grass analogy, the more hands that plant in our AI soil, the greater our businesses will grow. Details at this article.

Autoencoders in Chemistry | Day 74

• Machine Learning application solved a common problem in synchrotron X-ray experiments by reducing the noise, also known as meaningless information present in the data and replaced these noisy targets with noise-free input signals. The ML concept they used was autoencoders. Overview is given as item 91 here or accessed directly through here while the detailed scientific publication can be found here.

Top Youtube Channels for learning Data Science | Day 75

• Made a list of perfect materials on Youtube to learn Data Science / Machine Learning:

1. StatQuest with Josh Starmer: if you’re new to Data Science, being able to understand the concept of Statistics and Machine Learning can be difficult. John Starmer joined YouTube on May 24, 2011, and currently has 895K subscribers. Starmer uses the concept of images to help you understand complex topics and slowly builds up your understanding. I used StatQuest when I first dived into Data Science when I realised how important it is to understand the concept of Statistics. He starts off his videos with a short catchy introduction to him singing to break the ice and also make you feel at ease about learning complex theory.

2. Krish Naik: Krish Naik is the cofounder of iNeuron and has over 10 years of experience in machine learning, deep learning, and computer vision. Krish Naik joined YouTube on Feb 11, 2012, and currently has 731K subscribers.
   Not only does Naik speak on the theory and applications of Data Science, Machine Learning, Deep Learning, and more; he also gives advice and guidance on entering and building yourself within the field. He also has three different types of Memberships on his YouTube channel; DataScience Materials, Data Science Guidance, and Projects Live DataScience.

3. Simplilearn: Simplilearn joined YouTube on Oct 29, 2009, and currently has 2.9M subscribers. They aim to help people acquire the skills they need to thrive in the digital economy, which is currently taking over. They offer courses, and comprehensive certification programs, and have partnerships with world-renowned universities. Their approach has resulted in 85 percent of their learners receiving promotions or landing new jobs. Not only do they give comprehensive theory-based and application use of everything digital-related; they also have videos of trends in the current market aswell as top books for self-development.

4. freeCodeCamp.org: freeCodeCamp.org is an organisation that allows you to learn to code for free. They joined YouTube on Dec 16, 2014, and currently have 7.42M subscribers. The channel was started by Quincy Larson, who has created thousands of coding tutorials and videos and has thousands of freeCodeCamp study groups around the world. If you are unsure if coding is for you and want to test the waters first, freeCodeCamp.org is a good place to start as you don’t have the pressures of finances over your head.

5. Edureka!: Edureka! is a live & interactive e-learning platform that joined YouTube on Jun 29, 2012, and currently has 3.72M subscribers. They offer instructor-led courses, which have 24/7 on-demand support along with real-life projects, to ensure their pupils learning goals are met. They have a wide range of topics such as Data Science, Artificial Intelligence, Big Data, DevOps, Blockchain, Python, Selenium, Tableau, Android, AWS Architect, Digital Marketing, and more. They also provide information about the top trending companies, highest paying jobs, programming languages, and certificates to get you prepared for the sector.

6. Corey Schafer: Corey Schafer focuses on creating tutorials and walkthroughs for software developers, programmers, and engineers. Schafer joined YouTube on May 31, 2006, and currently has 1.08M subscribers. Schafer's content is not based on a particular skill level as he caters to beginners to people with years of experience. Schafer covers a variety of topics such as Python, Git, Terminal Commands, SQL, JavaScript, Computer Science Fundamentals, and more.

7. sentdex: sentdex provides Python Programming tutorials, from the basics to the complex. Sentdex joined YouTube on Dec 16, 2012, and currently has 1.22M subscribers. Sentdex has a variety of topics covered in tutorials such as machine learning, finance, data analysis, robotics, web development, game development, and more. Sentdex videos are not long in comparison to other YouTube channels, however, he still provides all the information required to understand the topic, This makes his video useful for people who want the information, and get easily demotivated from long videos.

8. Joma Tech: if you are already undergoing your Data Science journey, but you need a bit of advice about the sector and what’s trending in the market, Joma Tech is the person for you. Joma Tech talks about life in Silicon Valley and major tech companies. Joma Tech joined YouTube on Aug 31, 2016, and currently has 2.15M subscribers. He gives you the truth about what you will be doing as a Data Scientist, Engineer, etc, as well as information about the hiring process.

GPT4 | Day 76

• Fantastic how efficient GPT4 to its predecessor ChatGPT (GPT-3.5) has become. Its advantage over the predecessor to generate multimodal content which means it can produce images, audio and other types of media apart from text is amazing. A look at what we already know it can do can be found here. If you also wish to get the most out of GPT4 by making correct prompts view this tweet here. Additionaly let's go in history and see what OpenAI's Chief Scientist said about the potential of multimodal AI back in 2020 as found here.

NLP | Day 77

• NLP is more than chatbots and text summarizers. It helps power image, video, music generators and more. This comprehensive guide as item 91 here or accessed directly through here covers how it works, where it is being applied, top techniques, libraries and frameworks to name some of the things that are covered. If you also fancy how to leverage AI to boost your productivity and accelerate your career take a look at this newsletter.

SQL Interviews & Python Cheatsheet | Day 78

• Stumbled across a great article on SQL interview questions for professionals as can be accessed through here as well as a Python cheatsheet that can be found here.

Big O Cheatsheets & Algorithms for MLOps| Day 79

• Irrespective of how it is thought I believe grasping Big O notation for data structures and algorithms to use as an ML/MLOps Engineer or any kind of a developer is essential and will boost your career. Knowing which algorithm to use and understanding Big O will boost your MLOps approach when deploying a model and save enormous time as well as give you surprising career benefits. Even though I know it might be difficult to grasp the concept of algorithms, hence I recommend reading the visual book on the algorithms as item 1 here or more technical one as item 2 here to understand them better. More details on them under Day 8.
• Regarding the Big O notation for data structures. The cheatsheets could be accesed as item 92 here and 93 here and looked upon below.

GPT4 Again | Day 80

• Read a study about the impact of GPTs' on the US labor market that shows surprising figures:
  • ~ 80% of the workers may have at least 10% of tasks affected
  • ~ 19% of workers may see at least 50% of tasks impacted The article could be found as pdf here or as an article on arxiv.org here.
• GPT4 might also have some flaws like it is constrained by an extensive set of human-crafted “guardrails” that seek to prevent it from being offensive or off the wall, it doesn’t update its knowledge in real time, its command of languages other than English is limited, it doesn’t analyze audio or video and it still makes arithmetic errors that a calculator would avoid but the prospect for the future of OpenAI is bright. Those very likely will be overcome with GPT5. More about that here.

Generative AI & GPT 4 Bot | Day 81

• Read an overview of recent generative AI techniques and applications. Simply put Generative AI can be thought as Artificial Intelligence Generated Content (AIGC) that which involves the creation of digital content, such as images, music, and natural language, through AI models. The goal of AIGC is to make the content creation process more efficient and accessible, allowing for the production of high-quality content at a faster pace. Details can be found as item 95 here or accessed directly through here.
• Found a fantastic tutorial to make a Twitter GPT Bot as details are here.

Copilot X & AI Book | Day 82

• Started using a renewed GitHub Copilot that adopts GPT-4 as part of collaboration between Microsoft and OpenAI. As they say they are not only adopting OpenAI’s new GPT-4 model, but are introducing chat and voice for Copilot, and bringing Copilot to pull requests, the command line, and docs to answer questions on your projects. What that means is that they included Copilot Pull Requests and a chat interface ran on GPT-4 integrated with VS Code and Visual Studio. More details here.
• Came across an amazing free book titled "How to Build Your Career in AI" by Andrew Ng on his insights about learning foundational skills, working on projects, finding jobs, and community in machine learning as can be accessed as item 14 here or directly here.

ChatGPT Awesomness, RNN, MLOps & DL | Day 83

• ChatGPT can now browse the internet. More here.
• Found how to construct a website using ChatGPT as given here.
• Dived into building an RNN with Python. A great tutorial on creating it from scratch can be accessed here.
• Started refreshing about MLOps and found this summary useful. It provides the best GitHub repositories for learning.
• Finally came across a cheatsheet to Deep Learning algorithms that could be read through here.

Top Channels for Machine Learning | Day 84

Made a refreshed list¹ of Youtube Channels to learn Machine Learning now:

1. DeepLearningAI

Subscribers: 203 K, Videos: 333, Views: 13.5 M, Link: DeepLearningAI

DeepLearningAI is founded by Andrew Ng, a well-known AI researcher who founded Google Brain. His deep learning specialization on Coursera has a huge global following. The channel offers a variety of educational content, including video lectures and tutorials, interviews with experts in the field, and live Q&A sessions. It also keeps the viewers updated with the latest trends in the field of Machine Learning and Deep Learning.

3. Artificial Intelligence — All in One

Subscribers: 158 K, Videos: 525, Views: 17.7 M, Link: Artificial Intelligence - All in One

It is a comprehensive resource that provides a one-stop shop for all the things in Artificial Intelligence. It includes tutorials, videos, and other resources about the fundamentals of AI, machine learning, deep learning, computer vision, natural language processing, and more. The content is designed to be accessible to individuals with a wide range of backgrounds and skill levels, from beginners to experts.

4. Two Minute Papers

Subscribers: 1.4 M, Videos: 770, Views: 119 M, Link: Two Minute Papers

It's an amazing channel hosted by Konrad Kording that provides a summary of the latest research papers in form of short videos. The video covers the key findings, contributions, and implications of the research. This channel is particularly useful for practitioners, researchers, or anyone who wants to keep themselves updated about the latest developments.

5. Kaggle

Subscribers: 124 K, Videos: 351, Views: 3.6 M, Link: Kaggle

Kaggle is one of the most renowned platforms for data scientists and machine learning practitioners to polish their skills. This youtube channel not only covers various tutorials for beginners and intermediate-level audiences but also features interviews with industry gurus. They also share winning solutions of the Kaggle competitions that help the audience to learn from the experts.

6. Applied AI Course

Subscribers: 83.4 K, Videos: 517, Views: 13.8 M, Link: Applied AI Course

As the name suggests, this channel focuses more on practical knowledge rather than theoretical rigor. It teaches the core ideas of Machine Learning and works on real case studies that enable an individual to deal with real-world business problems and build their AI solutions.

7. Jeremy Howard

Subscribers: 73.6 K, Videos: 164, Views: 7 M, Link: Jeremy Howard

Jeremy Howard is the co-founder of fast.ai and is well-known for his contributions to the field of deep learning. The purpose of his channel is to make AI accessible to everyone regardless of their backgrounds. Therefore, his video lectures are easy to understand and follow.

8. Siraj Raval

Subscribers: 739 K, Videos: 450, Views: 48 M, Link: Siraj Raval

Siraj Raval is a well-known figure in the field of Machine Learning. His youtube channel covers topics related to machine learning, deep learning, computer vision, natural processing language, etc. His fun and engaging approach to teaching is what makes his content unique and easier to digest.

9. Daniel Bourke

Subscribers: 147K, Videos: 299, Views: 7 M, Link: Daniel Bourke

Daniel Bourke is the instructor of one of the bestseller courses on Udemy, PyTorch for Deep Learning in 2023: Zero to Mastery. He is a self-taught machine learning engineer who has worked with a wide range of industries. Daniel takes you step-by-step from an absolute beginner to becoming a master in the field of Machine Learning.

10. Data School

Subscribers: 216K, Videos: 139, Views: 10.8 M, Link: Data School

Kevin Markham is a data science educator and the founder of dataschool.io. This channel provides in-depth tutorials, webinars, and resources to help individuals build the skills they need to succeed in their professional careers. His channels are famous for clear, concise, and step-by-step explanations of complex concepts.

11. 3Blue1Brown

Subscribers: 5.05 M, Videos: 128, Views: 329 M, Link: 3Blue1Brown

This channel by Grant Sanderson is known for explaining complex mathematical and machine-learning concepts through appealing and intuitive animations. This channel is aimed towards a broader audience and is considered one of the best channels for Maths, Data Science, and ML

12. Jeff Heaton

Subscribers: 75.3 K, Videos: 554, Views: 5.9 M, Link: Jeff Heaton

Jeff Heaton is the creator of one of several popular books that can be found here. He uses real-world examples to explain complex concepts. He teaches concepts related to machine learning, deep learning, AI, etc. It is a great primer for beginners before diving deeper.

13. Machine Learning Street Talk

Subscribers: 47.8 K, Videos: 122, Views: 1.6 M, Link: Machine Learning Street Talk

This channel is managed by Tim Scarfe. It has regular cameos with Keith Duggar and Yannic Kilcher. This channel covers the latest development in the field of AI and ML. They provide high-quality content and invite the leading thinkers in the AI space to cover the current affairs in AI with in-depth analysis.

¹ Aditional 8 Youtube Channels at Day 75.

LLaMA | Day 85

• Studied a paper on LLaMA, a new LLM model, while detailed article explanation on it could be found here. I will not go into technical details on it just the prospects. It could help automate various business processes, from content generation to data analysis. For example, LLaMA could generate product descriptions, website copy, or even entire articles with just a few prompts that could save businesses significant time and resources while improving their content quality. Another potential use case for LLaMA would be in the realm of cybersecurity. For example, LLaMA could analyze and interpret vast amounts of text data, such as emails or social media posts, to identify potential security threats or attacks.

The Ultimate 100 AI Tools | Day 86

• Found 100 AI tools that will hone your productivity a lot. Some tools as Chrome extensions that I use are Magical AI, ConversAI and Eightify. More here.

GPT Guide | Day 87

Created a presentation on GPT covering ChatGPT and GPT4.

GPT4 in Medicine | Day 88

Listened YouTube video about the prospects of GPT4 in medicine. For example, it showed that it passed American Medical Exam up to level 3 with an accuracy of 90%. Apart from that, it concluded that GPT4 as a research assistant could help researchers and medical specialists/doctors hone their abilities to perfection by making use of it. Amazing.

Generative AI and Prompt Engineering for DS | Day 89

Found a great ebook on the latest trends and techniques to unlock the full potential of AI in various applications. It aims to provide a comprehensive guide on generative AI and prompt engineering, equipping readers with the knowledge and tools necessary to excel in the realm of datascience. Generative AI encompasses a range of models and techniques designed to generate new data based on existing input data. These models have demonstrated significant capabilities in natural language processing, image generation, and more. By understanding the mechanics and intricacies of generative AI, data scientists can harness its power to create innovative solutions for a multitude of problems. Prompt engineering, on the other hand, deals with the art of crafting eective prompts to guide AI models in generating desired outputs. As AI models become more sophisticated, the need for efficient and precise prompt engineering has grown more critical. By mastering this skill, data scientists can better direct AI models to produce targeted results, ultimately enhancing the efficacy of their applications. It delves into the key concepts, best practices, and real-world applications. More at the book through pressing the link above.

ChatDoctor | Day 90

• Experimented with ChatDoctor (publication also available as item 96 here) that shows great potential to understand patients' needs, provide informed advice, and offer valuable assistance in a variety of medical-related fields by looking over 700 diseases. The integration with LLaMA into healthcare can revolutionize the way healthcare professionals and patients communicate, ultimately improving the overall efficiency and quality of patient care and outcomes. Want to try it - go to item 12 here and play with it.

ChatGPT Outperforms Crowd-Workers | Day 91

Read and analysed a publication on how ChatGPT outperforms crowd-workers for text-annotation tasks. Fascinating that ChatGPT outperforms crowd-workers for several annotation tasks, including relevance, stance, topics, and frames detection and is much more cost efficent than MTurk. Article here.

Data Science from GitHub | Day 92

Made a list on how to learn about Data Science from these Github respositories:

1. Data Science For Beginners: One of the best GitHub repositories I have come across! This repo provided by Azure Cloud Advocates from Microsoft offers a 10-week, 20-lesson curriculum to help you break into data science. The lessons include a pre-lesson that is followed by a post-lesson quiz, written instructions on how to complete the lesson, with a solution, and an assignment. This covers the basics of data science and is aimed at beginners. You will cover aspects such as data science ethics, introduction to statistics & probability, visualizing relationships, and more.

2. Free Data Science Books: If you’re a bookworm and the best way for you to learn is by flicking through pages - this GitHub repo has come to save the day. Not only does it provide a list of books that follow a curriculum, it's FREE! The books will state their difficulty level with beginner, intermediate, or veteran next to it. The topics covered include Data Science Introduction, Data Processing, Data Analysis, Data Science Application, Data Visualization, Uncategorized, and MOOCs about Data Science.

3. Data Science Curriculum: When starting out on your roadmap to data science, it can be difficult to know where to start. This is the problem I had, and a lot of people I know. Following a curriculum will allow you to manage your time well, ensure you hit all the data science aspects and realize where your weaknesses are so you can work on them. This data science curriculum provided by Open Source Society University gives you a list of courses that you need in order to become a data scientist. They may not have the materials there for free, but having a study plan makes your life much easier.

4. Awesome Data Science: Similar to a curriculum, this Awesome Data Science GitHub goes through all the nooks and cracks of data science. If you are the type of person that needs to know the topics you require to become a data scientist, but want to go and do your own research, this GitHub repository is for you. It’s the toolbox to data science. It provides you with books, blog articles, web pages and more on everything you need to know about data science. They also give you more information on free courses, intensive programs and colleges that can kickstart your data science career.

5. Data Science All Cheat Sheet: Cheat sheets are a great way to learn something new. They provide you with the basic information and allow you to go off and study about it more. The owner pulled together these cheat sheets and aimed to help students achieve comprehensive content that provided clarity.

6. Best of ML with Python: This Best of ML with Python GitHub repository provides you with 910 open-source projects grouped into 34 categories. The projects are ranked by a project-quality score, so you can see which projects are popular with a description of what the project entails. You have categories such as data loading & extraction, model interpretability, medical data, and more.

7. Data Science Interview Resources - Interview Questions: The hard skill questions you will be asked during a data science interview will typically be based in two categories: theoretical and technical. This GitHub repo goes through both and helps you test your knowledge in order to prepare for your interview. They also give you tips on building your resume/CV, which is an important aspect when trying to win over the recruiter.

5 AI tools, ChatGPT Plugin, Survey, Book | Day 93

• Here are my 5 AI intergrations that I use almost daily:
  1. Slides AI that generate beautiful slides and compelling presentations with AI in seconds.
  2. Stability AI - Photoshop's AI plugin powered by Stable Diffusion - that helps create, edit, and iterate AI images directly within Photoshop.
  3. Kickresume AI that helps land more job interviews.
  4. Perplexity AI for IPhone that is a search app providing instant answers and cited sources on any topic.
  5. Gamma AI - a GPT-4 powered app - that creates compelling presentation decks in minutes. With Gamma it is possible to create engaging presentations, memos, briefs, and docs that are easy to discuss live or share async.
• Experimented with ChatGPT Retrieval Plugin that lets you easily search and find personal or work documents by asking questions in everyday language.
• Survey on LLM introduces the background, key findings, and mainstream techniques while focusing on pre-training, adaptation tuning, utilization, and capacity evaluation of LLMs.
• Amazon already sells a book on ChatGPT.

AUTO-GPT, Vicuna-13B & AI Model for Cancer | Day 94

• Joined open-source development of Auto-GPT that is an experimental open-source application showcasing the capabilities of the GPT-4 language model. It autonomously develops and manages businesses to increase net worth. To try it and join yourself look at it as item 13 here or access directly here.

• New chatbot just arrived as Vicuna-13B that is an open-source chatbot trained by fine-tuning LLaMA on ~70K user-shared ChatGPT conversations. It claims to achieve "more than 90% quality of OpenAI ChatGPT and Google Bard while outperforming other models like LLaMA and Stanford Alpaca in more than 90% of cases". Seems possible to run it on your own machine with a single GPU. Details as item 14 here or accessed directly the repo here and blog here

• Researchers from University of British Columbia developed an AI model that predicts cancer patient survival with accuraccy of above 85%. Details in the publication is here.

Trends in Artificial Intelligence | Day 95

Some trends of Artificial Intelligence from 2010s to nowadays as given by AI Index Report from Stanford University:

AI research has been heating up for years, with no signs of slowing down

AI models are getting big, and fast

New AI models today get MILLIONS times more training than 10 years ago

With great power comes great responsibility. People are also using these more capable AI models to do questionable things, like deepfaking politicians.

This number is going to continue to skyrocket as the world figures out how to adjust to new AI capabilities. Notable ones include the outstanding lawsuit against Stability AI for copyright concerns.

Governments are sprinting to figure out their approach to AI. Look at the EU. They've been working on their big AI Act for nearly 2 years. Then ChatGPT comes out and throws a big wrench in their framework. Kneejerk reaction from Italy to ban it.

Newly funded AI startups has ~tripled in the last 10 years. 57 of 273 companies in the most recent YC batch is doing work with generative AI.

It's a good time to have AI-related skills.

By comparison, people in China believe in AI's future way more than people in the US. What about Lithuania?

Overview of ChatGPT & GPT-4 | Day 96

Read a fantastic overview of ChatGPT and GPT-4 applications that was recommended by @omarsar0 on Twitter.

To sum up, these LLMs are analysed by studying 194 relevant papers and discussing capabilities, limitations, concerns, and more.

I second him that this is a great read for AI developers and researchers.

Prompt Engineering | Day 97

Found an awesome prompt engineering guide as accessed as item 15 here or straight here that contains all the latest papers, learning guides, lectures, references, and tools related to prompt engineering. Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.

Machine Learning Projects & Data Science | Day 98

• Found a great GitHub repo of curated Machine learning list that contains 910 awesome open-source projects with a total of 3.7M stars grouped into 34 categories. Can be found as item 16 here or accessed directly here.

• Other fantastic GitHub repos that give tips on how to begin the path of Data Science career and how to land your dream job as a Data Scientist can be found as item 17 and 18 here and here or accessed dirctly though here and here.

Awesome Data Science & ALL Cheatsheets | Day 99

• Took today easier due to Easter holiday and found an open source Data Science repository to learn and apply data science skills towards solving real world problems as can be inspected as item 19 here or accessed directly through here.

• Found ALL cheasheets ranging from Artificial Intelligence to Data Engineering to Machine Learning to Linux to Mathematics to R to Matlab and many more fields. The cheatcode can be found as item 97 here or accessed directly through here.

Public

(Back to top)

Public folder contains two files:

• todolist - the TO DO List.
• Images - the Images folder.

Jupyter in Browser

(Back to top)

First nice thing is that you could run Jupyter also through browser by doing so going here and reading more about it in this article.

If you find difficulty in running Jupyter Notebook through Browser then you could use Google Colab by clicking here. Functionalities of both machines are similar.

Logo

(Back to top)

The Logo of the repository can be found here.

License

(Back to top)

The MIT LICENSE can be found here.