EECS 545: Machine Learning

This is a graduate introduction to Machine Learning.

I am a Graduate Student Instructor for the Winter 2025 offering of this course under Professor Honglak Lee. Here’s a brief outline of the course content.

• Introduction
• Regression (Linear regression, Gradient descent, Maximum likelihood)
• Classification (kNN, Naive Bayes, LDA, Logistic regression)
• Kernel methods (KDE, SVMs)
• Regularization (L1 and L2, Feature selection, Bias-Variance tradeoff)
• Neural Networks and Deep Learning (Perceptron, MLP, Backpropagation, CNNs, RNNs, Transformers)
• Learning Theory (Sample complexity, VC Dimension, PAC Learning, Error bounds)
• Unsupervised Learning (k-Means, GMMs, Expectation Maximization, PCA, ICA, Dimensionality reduction, Autoencoders, GANs)
• Reinforcement Learning (MDPs, Value & Policy iteration, Policy gradient, Deep RL, Human feedback, Direct preference optimization)