Lectures

• Lecture 1: Introduction

• Lecture 2: Overview of Statistical Learning

  Reading Recourse: Chapter 5 of deeplearningbook
  

• Lecture 3
• Lecture 4: Linear Classification

• Lecture 5: Multilayer perceptron (Feedforward DNN)

  Reading Resource: Chapter 6.1, 6.2, 6.3 of deeplearningbook
  

• Lecture 8: Backpropagation

  Reading Resource: Chapter 6.5 of deeplearningbook
  

• Lecture 9: Optimization

  Reading Resource: Chapter 8.1,8.3,8.5 of deeplearningbook
  

• Lab: A simple Model for MNIST

• Lecture 10: Convolutional Neural Networks

  Reading Resource: Chapter 9 of deeplearningbook
  

• Lecture 11: Training DNN

  Reading Resource: Chapter 7.12, 8.4, 8.7 of deeplearningbook
  

• Lecture 12: Word Embedding

  Reading Resource: Chapter 6.8 of [Speech and Language Processing. Daniel Jurafsky & James H. Martin.](https://web.stanford.edu/~jurafsky/slp3/)
  

• Lecture 13: Recurrent Neural Network

  Reading Resource: Chapter 9 of [Speech and Language Processing. Daniel Jurafsky & James H. Martin.](https://web.stanford.edu/~jurafsky/slp3/)
  

• Lecture 14: LSTM Networks

  Reading Resource: Chapter 9 of [Speech and Language Processing. Daniel Jurafsky & James H. Martin.](https://web.stanford.edu/~jurafsky/slp3/)
  

• Lecture 15: Attention and Machine Translation

  Reading Resource: Chapter 13 of [Speech and Language Processing. Daniel Jurafsky & James H. Martin.](https://web.stanford.edu/~jurafsky/slp3/)
  

• Lecture 16: Transformers

  Reading Resource: Chapter 10 of [Speech and Language Processing. Daniel Jurafsky & James H. Martin.](https://web.stanford.edu/~jurafsky/slp3/)
  

• Lecture 17: Pretrained Models:BERT, GPT

• Lecture 18: Neural Tangent Kernel

• Lecture 19: Diffusion Models

  Reading Resource:Score-Based Generative Modeling through Stochastic Differential Equations

• Lecture 20: Graph Neural Networks

• Lecture 21: Information Theory of Neural Networks

• Lecture 23: Generative Adversarial Network

• Review notes

---

Table of contents

• Pytorch Tutorial