Home
Syllabus
Grading
Textbook

CSE512: Machine Learning

Fall 2018, Time: Tues & Thurs 1-2.20pm, ENGINEERING 145
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 you are not a Computer Science student, but believe that you have right prerequisites, complete THIS FORM to enter the queue for enrollment. The admin staff and I will process all special requests at the beginning of the Fall semester. Do not complete the form if you can enroll on Solar.

If both the class and the waitlist on Solar are full, do not send me an email. If you are still interested in taking the course, just come to the first two weeks of classes. Some spaces will be freed as some students will drop the course once they understand what machine learning really is. There is no guarantee though.

Homework 1 has been released. It is due Tuesday Sep 4 at midnight.

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
28-Aug-2018 Course introduction Andrew Moore's tutorial on probability Murphy's Chapter1 HW1 out
30-Aug MLE & MAP Mitchell's New Chapter on MLE and MAP
4-Sep Linear Regression Bishop's Section 3.1 and 3.3 HW1 due. HW2 out
6-Sep Bias-Variance Tradeoff Bishop's Sect. 3.2
11-Sep Ridge & LASSO Regularization, guest lecture By Prof. Ritwik Banerjee Bishop's Section 3.1 and 3.3
13-Sep Logistic Regression, guest lecture by Prof. Niranjan Balasubramanian HW2 due
18-Sep Naive Bayes HW3 out
20-Sep
25-Sep
27-Sep Generative versus Discriminative Classifier
2-Oct SVM, max-margin concept and primal formulation HW2 due. HW3 out.
4-Oct SVM, Duality
9-Oct Fall break - No class
11-Oct Dual SVM and Kernel trick
16-Oct Mid-term exam Midterm
18-Oct Boosting. HW3 due. HW4 out.
23-Oct K-means and PCA
25-Oct GMM, EM Algorithm
30-Oct Neural Networks
1-Nov Deep Learning HW4 due. HW5 out.
6-Nov CNN
8-Nov GAN
13-Nov RNN
15-Nov Reinforcement Learning HW5 due. HW6 out.
20-Nov Reinforcement Learning
22-Nov Thanksgiving - No class
27-Nov Reinforcement Learning
29-Nov Final class HW6 due
4-Dec NIPS - Guest lecture
6-Dec NIPS - Guest lecture
20-Dec Final exam Final 11:15pm - 1:45pm