CSE627: Advanced Machine Learning

This graduate-level course offers an in-depth theoretical exploration of machine learning, with a focus on both classical and modern techniques. Grounded in Bishop’s Pattern Recognition and Machine Learning (PRML), this course delves into the probabilistic and mathematical foundations of machine learning, making it distinct from the undergraduate applied courses.

Key Topics:

• Probabilistic Models: Bayesian networks, Markov models, and graphical models.
• Bayesian Learning: Bayesian inference and variational methods.
• Advanced Neural Networks: CNNs, RNNs, GANs, and deep generative models.
• Theoretical Treatment: In-depth analysis of optimization, overfitting, regularization, and model complexity.
• Reinforcement Learning: Policy gradients and advanced decision-making algorithms.

The course emphasizes building machine learning algorithms from scratch and applying them to complex datasets, distinguishing it from undergraduate courses which focus more on practical applications using libraries.

Textbook:

• Christopher M. Bishop, Pattern Recognition and Machine Learning (PRML)