CS 5350/6350 Machine Learning, Spring 2019

[Home] [Information] [Topics] [Lectures] [Projects]

Schedule

Mon & Wed at WEB 1250 04:35PM-05:55PM

Instructor: Shandian Zhe

Office MEB 3466
Email zhe at cs dot utah dot edu
Teaching Assistant: Yishuai Du (yishuai dot du at utah dot edu)
Teaching Mentee: Zhimeng Pan (z dot pan at utah dot edu)
Note:We have office hours EVERY weekday!
Office Hours       Instructor: Before the class, 3:30pm-4:30pm        Mon and Wed (MEB 3466)
Yishuai Du: Thu. 9:30AM - 11:00AM (MEB 3161)
Zhimeng Pan: Tue. 3:30PM - 4:30PM, Fri. 2:30PM - 5:00PM (MEB 3161)

Syllabus

Overview

This course introduces basic knowledge of machine learning. Topics consist of several fundamental, and widely successful supervised/unsupervised learning algorithms, such as decision trees, perceptrons, (deep) neural networks, kernel methods, support vector machines and Bayesian methods. Through this class, we hope that you will

1. understand machine learning ideas and paradigms,

2. be able to design identify or formulate appropriate machine learning problems for your research or applications,

3. be able to design machine learning models and (use existing tools) to implement learning algorithms. 

Grading

The grades are based on the following components:

The grades will be curved separately for undergraduate and graduate students. Extra problems may be included (merely) for graduate students.

Assignments must be electronically submitted through Canvas by midnight of the due date. Instructions about submission will be given in each assignment. Hand written versions or scans will not be accepted.

Instructions for programming assignments

  1. You are highly suggested to use MATLAB, Python and/or R for the programming portion of the assignments or projects. However, you can choose any other programming language. But you should guarantee that your programs can be compiled and run on the  CADE machines; otherwise you will NOT receive credits from the programming parts.

  2. Please include a README.txt file in your submission so that the TAs or the instructor can follow the instructions to test your code. Absence of the readme file will result in 0 grades for the submission.

Late policy

All assignments should be submitted by the deadline. If the deadline is missed, the late submissions will have 10% penalty. In every subsequent 24 hours, the late submissions will loose another 10% credicts. For example, a 10 points assignment will have 2 points penalty, if it is submitted 30 hours late. However, if the assignment is not turned in until the other assignment have been graded and returned or 48 hours after the deadline, 0 grade will be given.