CS 539: Machine Learning :: Spring 2024

Primary Textbook is

• (Flach) Machine Learning: The Art and Science of Algorithms That Make Sense of Data by Peter Flach, Cambridge University Press.

Additional course readings will be drawn from the following textbooks:

• (LfD) Learning From Data by Y. S. Abu-Mostafa, M. Magdon-Ismail, and H.T. Lin., AML Book
• (Mitchell) Machine Learning by Tom Mitchell, McGraw Hill
• Machine Learning Lecture Notes by Andrew Ng
• (Sutton & Barto) Reinforcement Learning: An Introduction by Sutton and Barto, MIT Press
• (DLP) Deep Learning with Python by François Chollet, Manning Publications
• Selected Research Papers

Tentative Schedule (subject to change)

Class #	Date	Topic	Readings	Homework	Project
1	1/12	Course overview & Machine Learning, Framing a Learning Problem	Flach: Prologue & Ch. 1, The Discipline of Machine Learning
2	1/16	Supervised Learning & Decision Trees	Mitchell: Ch. 3
3	1/19	Decision Trees & Overfitting, Evaluation	Flach: 2.1-3.2	HW1 out
4	1/23	k-Nearest Neighbor, Linear Regression; Gradient Descent	LfD: 1.1, 3.1-3.2.1, Flach: 7.1, 7.2, 7.4 Optional linear algebra review Basis functions
5	1/26	Regularization, Linear Classification; Perceptron	LfD: 3.3		Form a team by Jan 25
6	1/30	Logistic Regression; Evaluation		HW2 out
7	2/2	Why Machine Learning Works: VC Dimension & Generalization Bounds	LfD: 2, 3.2.2, Learning Theory Notes
8	2/6	Neural Network	Deep Learning Backpropagation http://neuralnetworksanddeeplearning.com/chap2.html
9	2/13	Neural Network		HW3 out
10	2/16	Deep Learning	DLP: 5.1; Convolutional Neural Networks
11	2/20	Deep Learning
12	2/23	Deep Learning; Midterm Review	DLP: 6.2
13	2/27	Midterm Exam
14	3/1	Support Vector Machines	Flach: 7.3, LfD: 8	HW4 out
15	3/12	Project Workday (in-class)
16	3/15	Project Workday (in-class)			Proposal due by March 18 (updated)
17	3/19	Support Vector Machines	Flach: 7.5, Bennett
18	3/22	Ensemble Methods; Probability Review	Flach: 11	HW5 out
19	3/29	Naive Bayes;	Flach: 9.1, 9.2
20	4/2	Text Classification; Word Vectors	Generative Model Notes Distributed Representations of Words and Phrases and their Compositionality
21	4/5	Unsupervised Learning:  K-Means; GMMs; Dimensionality reduction: SVD	k-means clustering Flach 8.4 Mixture of Gaussians MMD 9.4 Flach 10.3
22	4/9	Markov Decision Process; Reinforcement Learning	Sutton & Barto: Ch. 3, Ch. 4, Ch. 6, RL notes
23	4/12	Transfer Learning
24	4/16	Final Exam Review; Transfer Learning	Attention Is All You Need BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
25	4/23	Distillation	Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
26	4/26	Final Exam
27	4/30	Project Presentation			Website and Slides due by April 30
28	5/1	Project Presentation			Peer & Self Evaluation Form by May 1