Develop-Packt's repositories
Introduction-to-Monte-Carlo-Methods
This course examines the Monte Carlo methods and its types and solves the frozen lake problem with Monte Carlo methods.
Introduction-to-Temporal-Difference-Learning
This module introduces temporal-difference learning and focuses on how it develops over the ideas of both Monte Carlo methods, and dynamic programming.
Playing-an-Atari-Game-with-Deep-Recurrent-Q-Networks
This module will look at how to build different variants of DRQN including DARQN to solve the problem of Atari game
Web-Scraping-with-Jupyter-Notebooks
Analyze and parse HTML responses, programmatically scrape web data, and utilize Pandas DataFrames to store, transform, and merge tables.
Advanced-Web-Scraping-and-Data-Gathering
Decode responses and extract text from the Request and BeautifulSoup libraries, read and scrape data from XML files, and implement regular expressions to practice advanced web scraping on APIs.
Aggregate-and-Window-Functions
This module enables you summarize and identify the quality of the data using concepts such as aggregation and window functions.
Introduction-to-Jupyter-Notebooks
This course introduces the basic functions and features of Jupyter Notebooks, as well as major Python libraries.
Performing-Basic-Image-Operations
Perform geometric transformations, arithmetic operations, and image cropping using NumPy and OpenCV functions.
Reading-Data-from-Different-Sources
Read and handle data from HTML, JSON, and CSV files (among others), and practice web page parsing with BeautifulSoup4
Solving-the-Multi-Armed-Bandit-Problem
This module discusses the multi armed bandit problem and various strategies to solve it, introducing the concepts of state-rewards functions in RL and how to solve it using simple strategies
Training-Classification-Models
Apply data preprocessing methods to the Kaggle HR dataset and train machine learning models with scikit learn
A-Deep-Dive-into-Data-Wrangling-with-Python
Perform DataFrame operations in Pandas for a more in-depth look at data wrangling in practice
Advanced-Operations-on-Python-Data-Structures
Explore more advanced data structures in Python and how to handle them with some basic file operations
Exploratory-Data-Analysis
Perform exploratory data analysis techniques, such as predictive models and advanced visualization, on the Boston Housing Dataset.
Getting-Started-with-OpenAI-and-TensorFlow-for-RL
The module will cover OpenAI Gym environments, and essential concepts such as rewards, punishment and discounting factors. You will also look at implementing custom environments in Tensorflow 2
Importing-and-Analyzing-Data
This module covers the different ways in which we can move data between our database and our analytics tools. It also explores some of the advanced functionality in Python including SQLAlchemy and Pandas, which enabled us to perform data visualization.
Introduction-to-Dynamic-Programming
The module introduces dynamic programming using an example of coin-exchange. Then we go over to how and why it is used in Reinforcement Learning. The module also covers classic dynamic programming algorithms.
Introduction-to-Image-Processing
Study the components of image processing, and practice accessing and manipulating pixels in OpenCV and Matplotlib.
Introduction-to-NumPy-Pandas-and-Matplotlib
Implement advanced operations and data handling techniques on essential Python libraries to perform statistical descriptive analysis
Model-Optimization-and-Assessment
Practice model assessment and optimization on the HR dataset using validation and dimensionality reduction techniques
Performant-SQL
This module covers techniques to optimize query execution, such as creating indexes, and query planning, that improve performance. It will also introduce tools and techniques for terminating inefficient queries that are consuming our database resources.
Performing-Object-Detection-and-Facial-Recognition
Implement object detection and facial recognition techniques on input images and videos.
Practice-Deep-Learning-with-TF2
This module will cover Tensorflow 2 and show how to develop deep learning models and algorithms.
Preparing-Data-for-Predictive-Modeling
Develop classification strategies and preprocess data with pandas to prepare for predicative modeling.
Productionizing-your-AI-application-with-Docker
In this module you will look at how to take machine learning models into production, so that they can be used in live business applications. There are several methods of productionizing models, this module will cover a few of the common ones.
Relational-Database-Management-Systems-and-SQL
Review RDBMS structure, read data from SQL, and perform basic and advanced database operations for data retrieval
Scientific-Method-and-Applied-Problem-Solving
The course will help you uncover insights in a sample dataset using a case study approach. You will use all SQL queries to understand the cause for the dip in the pre-sales.
The-Hidden-Secrets-of-Data-Wrangling
Use generator expressions, formatting operations, and cleaning methods to prepare data for analysis.
Understanding-and-Describing-Data
This module will cover the role SQL in the world of data. It also introduces you to basic mathematical and graphical techniques to analyze data.
Working-with-Histograms
Build, adjust, and equalize histograms for image enhancement.