Syllabus (Tentative)
Introduction
Machine Learning Basics
Empirical loss minimization framework
Linear Classifiers
Nearest Neighbor Classifiers
Regularization
Non-linear Classifiers
Classifier complexity
Digit recognition case study
Neural Networks Basics
Back-propagation
Training a Neural Network
Neural Networks for Images
Convolutions and other building blocks
Detection
Dense Prediction
Sequence Modelling
Image Generation
Variational Auto-encoders
Diffusion Models
Generative Adversarial Networks
Advanced Topics
Self-supervision
Neural Radiance Fields
Large-language Models