CSCI 315 : Artificial Intelligence through Deep Learning


Professor: Simon D. Levy
Lecture: M/W/F 1:25 - 2:20 Parmly 307
Office: Parmly 407B
Office Phone: 458-8419
E-mail: simon.d.levy@gmail.com
Office Hours: Daily 2:30-3:30 and by appointment


Textbook: Our theme, Deep Learning, is too new to have a complete textbook. We will however use the three-chapter pre-release PDF edition of Nikhil Buduma's Fundamentals of Deep Learning for the second half of the course. For the first half of the course, will use online materials, based on my own lecture notes and on the assignments from the syllabus created by Prof. Michael Mozer at the University of Colorado.

Objectives

The goal of this course is to give you the skills and knowledge to participate in the exciting new field of Deep Learning. For the first half of the course you will learn to design, train, and test neural networks using the NumPy package in Python. In the second half of the course you will learn how to use the powerful Theano Python package to train and test much more powerful deep-learning networks that exploit the Graphical Processing Unit (GPU) available on our computers. In addition to being able to design, train, and test Deep Learning networks, you will gain an understanding of the history and philolsophy of AI, the current challenges it faces, and the prospects for the future.


Attendance and Preparation

I look at this course as preparation for professional work in a research or industry setting, and I expect you to act professionally: show up for every class, participate fully, and submit your work on time without excuses. Consistent with our university's mission statement, I expect everyone to conduct themselves with honor, integrity, and civility: if you are talking, texting, or otherwise causing a distraction in class, I will ask you to leave.


Grading

All work should be submitted through Sakai as Python .py files. The fast pace of the course means that no late work can be accepted.The only three exceptions to this rule are: As a way of helping with unanticipated emergencies and bad days, I will drop your lowest exam or project grade.Given the size of the class and the amount of work involved, there will be no opportunity for extra credit if you are not happy with your grade as the end of the course approaches. Serious problems (health / family / personal emergencies) should be handled through the Office of the Dean.

The grading scale will be 93-100 A; 90-92 A-; 87-89 B+; 83-86 B; 80-82 B-; 77-79 C+; 73-76 C; 70-72 C-; 67-69 D+; 63-66 D; 60-62 D-; below 60 F.


Final Project

In lieu of a big final example, I would like to see what kinds of cool projects you can devise. Given our resource constraints and large class size, I encourage you to work in teams of up to four people.

You may also elect to do a short (around 10 pages double-spaced) paper instead of a final project. This could be a discussion (with references of course) about a current issue of interest or controversy in AI. Here is a possible topic to look into.


Schedule, Including Due Dates and On-line Class Notes

For each exam, you are responsible for all linked material posted before that exam.

Theano

Monday

Wednesday

Friday

11 Jan
Week 1

Course Outline

What is (A)I?

The Myth of a Superhuman AI

Neural Net Intro Video
(sign up for Coursera)

Deep Learning Intro Article (PDF is on Sakai)

Bengio's Deep Learning Intro (Section I)

Why Neural Nets?

Linear Least Squares

18 Jan
Week 2

Martin Luther King Day: No Class

Lecture: Perceptron Learning

Reading: Nielsen Chapter 1

or Buduma Chapters 1-2

 Due: Assignment #1

25 Jan
Week 3

Continue: Perceptron Learning Limits of Perceptrons Review Weeks 1-3

Exam #1 (take-home)

01 Feb
Week 4

Back-propagation with hidden units  Due: Assignment #2

08 Feb
Week 5

Back-prop, continued Back-prop II: Improvements Mock Convention; no class

15 Feb
Week 6

Back-prop II, continued Logistic Regression & Soft-Max  Due: Assignment #3

29 Feb
Week 7

Logistic Regression & Soft-Max

Reading: Buduma Chapter 3 or Nielsen Chapter 3

Logistic Regression & Soft-Max  Exam #2

07 Mar
Week 8

Exam #2 follow-up Theano Overview Guest lecture by VMI Prof. John David

Due: Assignment #4

14 Mar
Week 9

Theano Theano Theano (conclude)

21 Mar
Week 10

Convolutional Networks

Reading: Nielsen Chapter 6

Convolutional Networks

Due: Final Project Proposal (email from team leader)

28 Mar
Week 11

Due: Assignment #5

04 Apr
Week 12

 Exam #3

11 Apr
Finals Week

 Project Presentations