Syllabus (Tentative)

  1. Introduction

  2. Machine Learning Basics

    1. Empirical loss minimization framework

    2. Linear Classifiers

    3. Nearest Neighbor Classifiers

    4. Regularization

    5. Non-linear Classifiers

    6. Classifier complexity

    7. Digit recognition case study

  3. Neural Networks Basics

    1. Back-propagation

    2. Training a Neural Network

  4. Neural Networks for Images

    1. Convolutions and other building blocks

    2. Detection

    3. Dense Prediction

    4. Sequence Modelling

  5. Image Generation

    1. Variational Auto-encoders

    2. Diffusion Models

    3. Generative Adversarial Networks

  6. Advanced Topics

    1. Self-supervision

    2. Neural Radiance Fields

    3. Large-language Models