CS 539: Machine Learning :: Fall 2022

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	8/24	Course overview & Machine Learning, Framing a Learning Problem	Flach: Prologue & Ch. 1, The Discipline of Machine Learning
2	8/25	Supervised Learning & Decision Trees	Mitchell: Ch. 3
3	8/29	Decision Trees & Overfitting, Evaluation	Flach: 2.1-3.2	HW1 out
4	9/1	k-Nearest Neighbor, Linear Regression; Gradient Descent	LfD: 1.1, 3.1-3.2.1, Flach: 7.1, Optional linear algebra review
5	9/8	Linear Regression	Flach: 7.1, 7.2, 7.4 Basis functions		Form a team by Sept 7
6	9/12	Regularization, Linear Classification; Perceptron	LfD: 3.3	HW2 out
7	9/15	Logistic Regression; Evaluation
8	9/19	Why Machine Learning Works: VC Dimension & Generalization Bounds	LfD: 2, 3.2.2, Learning Theory Notes
9	9/22	Neural Network	Deep Learning Backpropagation http://neuralnetworksanddeeplearning.com/chap2.html	HW3 out
10	9/26	Neural Network
11	9/29	Deep Learning	DLP: 5.1; Convolutional Neural Networks
12	10/3	Deep Learning; Midterm Review		HW4 out
13	10/6	Midterm Exam
14	10/10	Deep Learning
15	10/24	Project Workday (in-class)	DLP: 6.2		Proposal due by Oct 27
16	10/27	Support Vector Machines	Flach: 7.3, LfD: 8
17	10/31	Support Vector Machines	Flach: 7.5, Bennett	HW5 out
18	11/3	Ensemble Methods; Probability Review	Flach: 11
19	11/10	Naive Bayes; Text Classification; Word Vectors	Generative Model Notes Flach: 9.1, 9.2 Distributed Representations of Words and Phrases and their Compositionality
20	11/14	Unsupervised Learning:  K-Means; GMMs; Dimensionality reduction: SVD	k-means clustering Flach 8.4 Mixture of Gaussians MMD 9.4 Flach 10.3	HW6 out (optional)
21	11/17	Markov Decision Process; Reinforcement Learning	Sutton & Barto: Ch. 3, Ch. 4, Ch. 6, RL notes
22	11/21	Markov Decision Process; Reinforcement Learning
23	11/28	Transfer Learning
24	12/1	Hot topic: Active Domain Adaptation	· Active learning for domain adaptation: An energy-based approach · Active domain adaptation via clustering uncertainty-weighted embeddings · Multi-Source Domain Adaptation with Weak Supervision for Early Fake News Detection
25	12/5	Final Exam Review
26	12/8	Final Exam
27	12/12	Project Presentation			Website and Slides due by Dec 14
28	12/15	Project Presentation