This repository is about to document my journey in learning machine learning. It will include study materials such as PPTs in the "file" folder, as well as my code implementations and related references in the "code" folder. Through these studies, I aim to understand important foundational concepts like gradient descent, backpropagation, and optimizers, in preparation for future learning of LLM algorithms. Keep your hands dirty!
Machine Learning The machine learning course taught by Andrew Wu starts from the most fundamental topics such as linear regression and gradient descent, and progresses to deep learning, reinforcement learning, as well as explanations of some tree models. The lectures are clear and refreshing, making it an excellent introductory course.
Neural Networks and Deep Learning, a book + cs229 + back prop of transformer + back prop by hongyi Some explanations and code about the backpropagation algorithm, serving as a supplement to the aforementioned Machine Learning course.
Neural Networks: Zero to Hero + cs336 Building a transformer language model from scratch.
CMU10-714 vedio + CMU10-714 Some fundamental system knowledge, and diving into ML systems (mlsys).
Learning linear regression and gradient descent—the first machine learning algorithm I have studied!
Learning the backpropagation algorithm and implementing handwritten digit recognition—Hello World!