Lecture Notes and Slides

• Logistic Regression: From Binary to Multi-Class [Notes] [Slides]

• A Unified View of Loss Functions in Supervised Learning [Notes] [Slides]

• A Neural Network View of Kernel Methods [Notes] [Slides]

• Principal Component Analysis and Autoencoders [Notes] [Slides]

• Back-Propagation: From Fully Connected to Convolutional Layers [Notes] [Slides]

• A Mathematical View of Attention Models in Deep Learning [Notes] [Slides]

• Unsupervised Learning and Expectation Maximization [Slides]

These materials can be used freely for teaching and research purposes, as long as they are cited properly.
Bibtex is here.

Current

• Fall 2023: CSCE 421: Machine Learning

FAQ

Please read before sending inquiries.

• Can I audit your class?

• What if your class is full?

• What if I am not a CSCE student?

Past

• Fall 2022: CSCE 636: Deep Learning
  

• Fall 2021: CSCE 636: Deep Learning

• Fall 2020: CSCE 636: Deep Learning

• Fall 2019: CSCE 636: Deep Learning

• Spring 2019: CSCE 489: Machine Learning

• Fall 2018: CSCE 636: Deep Learning

• Spring 2018: CPTS 437: Introduction to Machine Learning

• Spring 2017: CPTS 483: Introduction to Machine Learning

• Fall 2016: CPTS 580: Deep Learning

• Spring 2016: CPTS 483: Introduction to Machine Learning

• Spring 2015: CS795/895: Machine Learning for Neuroimaging

• Fall 2014: CS722/822 Machine Learning

• Spring 2014: CS 361 Advanced Data Structures and Algorithms

• Spring 2014: CS 600 Algorithms and Data Structures

• Fall 2013: CS722/822 Machine Learning

• Spring 2013: CS795/895 Advanced Biological Data Mining

• Fall 2012: CS795/895 Machine Learning

• Spring 2012: CS600 Algorithms and Data Structures

• Spring 2012: CS795/895 Data Mining and Bioinformatics

• Fall 2011: CS795/895 Machine Learning

• Spring 2011: CS600 Algorithms and Data Structures

• Fall 2010: CS480/580 Introduction to Artificial Intelligence