About this project

This repository is a comprehensive collection of machine learning and deep learning code examples and tutorials, maintained by the author of deeplearningcourses.com. It serves as the companion codebase for a wide range of online courses spanning foundational statistics through advanced AI topics. The repository is organized by course, with each course occupying its own folder. Users are directed to watch the 'Where to get the code' lecture (typically Lecture 2 or 3) within each course to identify the corresponding folder. The author recommends cloning rather than forking the repository to stay up to date with frequent course updates. Topics covered across the associated courses include: - **Foundational Math**: Linear algebra, probability, calculus, and matrix calculus for data science and machine learning. - **Classical Machine Learning**: Linear regression, logistic regression, naive Bayes, support vector machines, random forests, AdaBoost, cluster analysis, and unsupervised learning with hidden Markov models. - **Deep Learning**: Neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), GANs, variational autoencoders, and advanced computer vision. - **Natural Language Processing**: NLP with deep learning, transformers, and advanced NLP techniques. - **Reinforcement Learning**: Deep reinforcement learning in PyTorch and Python. - **Generative AI**: ChatGPT and OpenAI LLMs in Python, generative AI for computer vision, and deepfakes/voice cloning. - **Bayesian Methods**: Bayesian linear regression, Bayesian classification, and Bayesian machine learning with A/B testing. - **Financial AI**: Financial engineering and AI in Python, including a ChatGPT pairs trading bot. - **Time Series**: Time series analysis, forecasting, and machine learning. - **Recommender Systems**: Recommender systems and deep learning in Python. - **Prerequisites**: The NumPy stack in Python, linear regression, and logistic regression as deep learning prerequisites. Beginning with TensorFlow 2.0 courses, newer code examples were moved to Google Colab notebooks, with links provided within the respective courses. The repository also links to VIP and exclusive courses covering specialized topics such as statistical inference, linear programming for linear regression, and MATLAB for STEM professionals. The repository is intended for students and practitioners seeking hands-on code examples to complement structured online learning. It is not a standalone library or framework but rather an educational resource that pairs with video lectures and course materials available on deeplearningcourses.com and lazyprogrammer.me.