CSE512: Machine Learning

Fall 2019, Time: Tues & Thurs 11.30am – 12.50pm, Javits 109
Instructor: Minh Hoai Nguyen, New CS 153.
TA: TBA. Office hours: TBA

This course is intended for graduate students who already have good programming skills and adequate background knowledge in mathematics, including probability, statistics, and linear algebra. This course is offered by the Department of Computer Science, and students from the department will have priority in registering for this course. If there are still spaces, students from AMS and BMI will be given special permission to enroll. Students from other departments won't be able to enroll in this course (due to resource constraint).

For special permission to enroll, complete this Request Form by Monday 9/2. No guarantee though.

Grading

There will be six homework assignments and two exams.

Six homework assignments: 60%
Midterm exam: 15%
Final exam: 25%

Weights are approximate and subject to change. You are expected to do homework assignments by yourselves. Even if you discuss them with your classmates, you should turn in your own code and write-up. You can have one sheet of paper with notes in the exams.

Tentative Syllabus

Date	Topic	Readings	Assignments
27-Aug-2019	Course introduction
29-Aug	MLE & MAP		HW1 out
3-Sep	Linear Regression
5-Sep	Bias-Variance Tradeoff		HW2 out
10-Sep	Performance evaluation
12-Sep	Regularization Ridge Regression
17-Sep	LASSO Regression and Sparsity
19-Sep	Bayes risk and Nearest Neighbor Classifier		HW2 due. HW3 out
24-Sep	Naive Bayes
26-Sep	Logistic Regression
1-Oct	SVM, max-margin concept and primal formulation
3-Oct	SVM, Duality		HW3 due
8-Oct	Dual SVM and Kernel trick
`10-Oct`	`Mid-term exam`		Midterm
15-Oct	`Fall break - No class`
`17-Oct`	`Posible mid-term exam` Boosting & Bagging, Decision Tree		HW4 out
22-Oct	K-means and PCA GMM
24-Oct	HMM
29-Oct	ICCV - Guest lecture
31-Oct	ICCV - Guest lecture		HW4 due. HW5 out.
5-Nov	Deep Learning
7-Nov	Training Deep Network
12-Nov	CNN
14-Nov	GAN		HW5 due. HW6 out.
19-Nov	RNN
21-Nov	Reinforcement Learning
26-Nov	Reinforcement Learning
28-Nov	`Thanksgiving - No class`
3-Dec	Reinforcement Learning
5-Dec	Final class – Review		HW6 due.
`18-Dec`	`Final exam`		Final 11:15pm - 1:45pm

Textbooks

Textbooks are optional.

Books that I love amd recommend:

Tom Mitchell, Machine Learning, McGraw Hill, 1997.
- Excellent book. Concise and well-explained. But it is quite old and does not cover recently developed concepts.
- Some New Chapters are available

Mohri, Rostamizadeh, Talwalkar, Foundations of Machine Learning, MIT Press, 2nd edition, 2018.
- Excellent book. Well-explained. Deep and mathematically rigorous. Suitable for mathematically inclined students.
- Free PDF is available
- Use discount code MTSR20 for 30% discount from MIT press

Sutton & Barto, Reinforcement Learning: An Introduction, MIT Press, 2nd edition, 2018.
- Excellent book on reinforcement learning. Well-explained concepts with lots of examples. This provides a systematic view of multiple RL approaches.
- For reinforcement learning, this is the book to read.

Other textbooks that may be more useful or accessible:

Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2011.

Kevin Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012.

Academic misconduct policy:

Don't cheat. Cheating on anything will be dealt with as academic misconduct and handled accordingly. I won't spend a lot of time trying to decide if you actually cheated. If I think cheating might have occurred, then evidence will be forwarded to the University's Academic Misconduct Committee and they will decide. If cheating has occurred, an F grade will be awarded. Discussion of assignments and projects is acceptable, but you must do your own work. Near duplicate assignments will be considered cheating unless the assignment was restrictive enough to justify such similarities in independent work. Just think of it that way: Cheating impedes learning and having fun. The assignments are meant to give you an opportunity to really understand the class material. Please also note that opportunity makes thieves: It is your responsibility to protect your work and to ensure that it is not turned in by anyone else. No excuses!

Disability note:

If you have a physical, psychological, medical or learning disability that may impact on your ability to carry out assigned course work, I would urge that you contact the staff in the Disabled Student Services office (DSS), Room 133 Humanities, 632-6748/TDD. DSS will review your concerns and determine, with you, what accommodations are necessary and appropriate. All information and documentation of disability is confidential.