dsai-asia / PDS

Programming for Data Science and AI

CP: Computer Programming for Data Science and AI course at dsai.asia

This repository contains common materials for delivery of the Computer Programming for Data Science and AI course in the Asian Data Science and Artificial Intelligence Master's curriculum (dsai.asia).

--

Some resource worth mentioning:

1. Lectures/Starters/0 - Reading Roadmap

• For those who wants to know what papers to read. I have listed ONLY the most important papers you need to read in the field of machine learning

2. Lectures/Starters/0 - Installation

• For newbies who have trouble installing Python and other tools

3. Lectures/Starters/0 - Course Notations

• Understanding notations is the first step towards conquering math, so take a look and familiarized with it

4. Lectures/Advanced

• These are lessons I do not intend to teach given the time limit. It is intended for self-study.

5. Self-Exercises

• Every Lecture has a lab folder containing the assessment and solution. Anyhow, I also compile a list of possible exercises for student's self learning inside the Self-Exercises folder.

6. AIT-2020

• The file "0. Course Introduction.ipynb" contains how I run the course. This course is a 15 weeks course, each week having two labs of 3 hours each. Each lab always end with the assessment and solution.

I would also like to give credits to several githubs that I have revised to create this:

• https://github.com/drgona/Pytorch_bootcamp_Udemy
• https://github.com/SethHWeidman/DLFS_code
• https://github.com/jakevdp/PythonDataScienceHandbook

The course is structured into 3 big components, mostly focusing on preprocessing and modeling perspectives:

(Note: For detailed information, please read "0 - Course Introduction")

1. Python Basics

Focus on getting started.

• Python
• Numpy
• Pandas
• Matplotlib
• Sklearn

2. Traditional Machine Learning

Focus on understanding the math + coding via coding from scratch

2.1 Regression

• Linear regression
• Polynomial regression
• Regularization

2.2 Classification

• Logistic regression
• Naive Gaussian
• Support Vector Machines
• Decision Trees
• K-Nearest Neighbors
• Bagging
• Random Forests
• Boosting - AdaBoost, Gradient Boosting

2.3 Clustering

• K-means
• Gaussian Mixture Models

2.4 Dimensionality Reduction

• Principal Component Analysis
• Manifold Learning

3. Deep Learning

3.1 Neural Network from Scratch

• Momentum
• Batch Norm
• Dropout
• Decay Learning Rate
• Glorot Initialization
• Activation Functions

3.2 PyTorch

• Basics
• ANN
• CNN
• RNN