Lectures

Introduction

(Topics, Policies, Overview of supervised, unsupervised, reinforcement, and deep learning)

Supervised Learning

(K-Nearest Neighbors, Linear Classification, SVM vs. Softmax Loss Functions)

Optimization

(Numerical vs. Analytic Gradient, Gradient Descent)

Neural Networks

(Activation Functions [Sigmoid, tanh, ReLU], Batch Normalization)

Decision Trees

(Entropy, Information Gain, Examples with Discrete & Numerical Attributes, Pros vs Cons)

Naive Bayes

(Probability Review, Naive Bayes Problems and Examples)

Ensemble Methods

(Multiple Models in ML, Bagging, Random Forest, Boosting)

Midterm Review

Introduction to Deep Generative Models (Guest Lecture)

(Autoregressive Modeling, Variational Autoencoder, Generative Adversarial Nets - GAN Model, Diffusion Models)

Transitioning from Supervised to Generative Learning (Guest Lecture)

(Logistic Regression for Generative Modeling, Monte-Carlo Estimation, Model Likelihood, Applications)

Reinforcement Learning