CS 480/697 Big Data Analystics
Course Syllabus
Fall 2016

COURSE Description

This class is designed for people who would like to understand more advanced machine learning and data mining tools to wrangle and analyze big data. The class will focus on various deep learning techniques. Students will be guided through the basics of various deep neural networks, using GPU, CUDA, OpenCL, and other tightly-coupled methods for big data parallel computing. The class will prepare students to perform predictive modeling and do basic exploration of large, complex datasets.

TEXT BOOK

Lecture notes and tutorials on GPU related big data parallel computing.
Deep Learning An MIT Press book in preparation, Ian Goodfellow, Yoshua Bengio and Aaron Courville

METHODOLOGY

Lecture and interactive problem solving.

APPRAISAL

Participation: 5% of the total
Assignments: 45% of the total
Two Examinations: 50% of the total
 

GRADING

91+ = A; 89+ = A-;
87+ = B+; 83+ = B; 80+ = B-;
77+ = C+; 73+ = C; 70+ = C-;
67+ = D+; 63+ = D; 60+ = D-;
0+ = F;

READING

We will read from the recommended text book, various sources on the web, and slides that will be made available on the web site. The schedule for the readings are given on the schedule web page.

OTHER POLICIES

1. Homework:
   • All homework must be typed not hand-written and must be submitted with the given cover page (Download the cover pages from the Assignments page).
   • Homework is due exactly at the prescribed time. No late homework is accepted.
   • Turn in the paper copy of a homework assignment in class and submit the softcopy of the assignment to your Unix account (detailed instructions will be given with each homework assignment).
   • Any questions or complaints regarding the grading of an assignment or test must be raised within one week after the score or the graded assignment is made available (not when you pick it up).
2. Providing answers for any examination when not specifically authorized by the instructor to do so, or, informing any person or persons of the contents of any examination prior to the time the examination is given is considered cheating.
3. Penalty for cheating will be extremely severe. Use your best judgment. If you are not sure about certain activities, consult the instructor. Standard academic honesty procedure will be followed for cheating and active cheating automatically results F in the final grade. Please check University Policy on Academic Standards and Cheating for additional information.
4. You are expected to come fully prepared to every class.
5. No incomplete grade under nearly all situations.
6. There is no formal attendance policy. However, you are responsible for everything discussed in class. You may receive a zero for lack of participation.
7. Pay very careful attention to your email correspondence. It reflects on your communication skills. Avoid using non-standard English such as "how r u?" in your email message. In addition, I recommend you put the class number 480/697 and a brief summary of your question in your email subject. For example,

   Subject: CS 480/697 A question on supervised learning

8. I immediately discard anonymous emails.
9. The ringing, beeping, buzzing of cell phones, watches, and/or pagers during class time is extremely rude and disruptive to your fellow students and to the class flow. Please turn off all cell phones, watches, and pagers prior to the start of class.

© Wei Ding, 2016, all rights reserved. This document is made available for use by the students of the class at the University of Massachusetts Boston. Copying, distribution or other use of this document without express permission of the author is forbidden. You may create links to pages in this web site, but may not copy all or part of the text without permission of the author.