CPSC 625-600 Artificial Intelligence:
Fall 2016

Syllabus

NEWS: 12/11/16, 07:57PM (Sun)
Read-Only Bulletin Board.: 9/7/16, 10:53AM (Wed)

Page last modified: 11/21/16, 08:48AM Monday.

General Information Resources Weekly Schedule Credits Lecture Notes Example Code Read-Only Board

I. General Information

Instructor:

Dr. Yoonsuck Choe
Email: choe@tamu.edu
Office: HRBB 322B
Phone: 979-845-5466
Hours: Tue/Thu 2:30pm-3:30pm

TA:

Randall Reams
Email: rcr344@tamu.edu
Office: HRBB 339
Office hours: MWF 11:30am-12:30pm

Grader:

Anavil Tripathi
Email: anaviltripathi@tamu.edu
* Grader does not hold office hours.

Prerequisite/Restrictions:

CPSC 311 or equivalent

Lectures:

Tue/Thu 3:55pm-5:10pm, ETB 1020

Goals:

To understand the problems in AI and to learn how to solve them:
  1. traditional methods in AI (search, pattern matching, logical inference, theorem proving, planning, etc.).
  2. modern approaches in AI (learning, probabilistic approaches, etc.).

Textbook:

Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (AIMA, hereafter), 3rd Edition, Prentice Hall, New Jersey, 2010.
Book Homepage

Computer Accounts and Usage:

  1. Computer accounts: if you do not have a unix account, ask for one on the CS web page. We will be using the CMU Common Lisp as our main language. You may use a different language but example code will only be made available in Lisp.
  2. CMU Common Lisp:

Topics to be covered:

See the Weekly Schedule section for more details.
  1. Introduction
  2. LISP
  3. Search
  4. Game playing, alpha-beta pruning
  5. Propositional Logic, first-order logic, theorem proving
  6. Planning
  7. Uncertainty, probabilistic approaches
  8. Learning
  9. Advanced topics

Grading:

  1. Exams: 50% (midterm: 20%, final: 30%)
    Make up exams:
    • There will be no make up exam for those who do not show up for the exam without 24 hour prior notice that is due to legitimate reasons.
    • For illness-related absence, explicit doctor's note of excuse (e.g. "<Full Name> is unable to attend classes on <Date> due to illness.") is required. Just a note acknowledging that you visited the doctor's clinic or student health center is not enough.
    • Make up exams will be different from the original exams although the difficuly will be adjusted to be comparable.
  2. Homeworks: 15% (about 3, 5% each)
  3. Programming Assignments: 30% (about 3: 10% each)
  4. Attendance: 5%
There will be no curving. The cutoff for an `A' will be 90% of total score, 80% for a `B', 70% for a `C', 60% for a `D', and below 60% for an 'F'.

Attendance is mandatory. Sign-in sheet will be distributed on random dates (about 10 times). More than 2 recorded absences will lead to 0% for attendance. Faked signatures will get 0% for attendance and an additional 15% penalty toward the final grade.

Late penalty: 1 point (out of 100) per hour. Late submissions will not be accepted 4 days after the deadline and/or after the solution has been posted.

Academic Integrity Statement:

AGGIE HONOR CODE: An Aggie does not lie, cheat, or steal or tolerate those who do.

Upon accepting admission to Texas A&M University, a student immediately assumes a commitment to uphold the Honor Code, to accept responsibility for learning, and to follow the philosophy and rules of the Honor System. Students will be required to state their commitment on examinations, research papers, and other academic work. Ignorance of the rules does not exclude any member of the TAMU community from the requirements or the processes of the Honor System.

For additional information please visit: http://aggiehonor.tamu.edu/

Local Course Policy:

Students with Disabilities:

The Americans with Disabilities Act (ADA) is a federal anti-discrimination statute that provides comprehensive civil rights protection for persons with disabilities. Among other things, this legislation requires that all students with disabilities be guaranteed a learning environment that provides for reasonable accommodation of their disabilities. If you believe you have a disability requiring an accommodation, please contact the Department of Student Life, Services for Students with Disabilities, or call 845-1637.

II. Resources

  1. LISP quick reference
  2. CMU Common Lisp (This one will be used in the class.)
  3. GNU Common Lisp
  4. My general resources page

III. Weekly Schedule and Class Notes

Week
Date
Topic
Reading
Assignments
Notices and Dues
Notes
1 8/30 Introduction Chapter 1   First day of class slide01
1 9/1 Introduction,
LISP
Chapter 26
26.1 and 26.2
Lisp quick ref
    slide01
slide02
2 9/6 Symbolic Differentiation Lisp quick ref     slide02
2 9/8 Uninformed Search (BFS,DFS,DLS,IDS) Chapter 3.1-3.6     slide03
3 9/13 Informed Search (BestFS,Greedy,A*) Chapter 4.1-4.3 (4.4 optional) Homework 1 announced.
See eCampus.
  slide03
3 9/15 IDA*,Heuristic Search,
Simulated Annealing, Constraint Satisfaction, etc.
Chapter 4, Chapter 6.1 Program 1 announced   slide03
4 9/20 Game playing
Min-Max, Alpha-Beta
Chapter 5     slide03
4 9/22 Game playing wrap up;
Representation, logic, frames
Chapter 5
Chapter 7
  Homework 1 due 9/25
Sunday 11:59pm
slide03
slide04
5 9/27 Guest Lecture by Dr. Thomas Ioerger Intelligent Agents. Lecture slides      
5 9/29 Guest Lecture by Jaewook Yoo Evolving Tool Use Behavior      
6 10/4 Propositional Logic Chapter 7 Homework 2 TBA   slide04
6 10/6 Theorem proving
First order logic (FOL)
Chapter 8; Chapter 9   Program 1 due slide04
7 10/11 Midterm Exam In class      
7 10/13 Theorem proving
for FOL
Chapter 8; Chapter 9 Program 2 TBA   slide04
8 10/18 Inference
for FOL
Chapter 9 Program 2 announced   slide04
8 10/20 Uncertainty Chapter 13   Homework 2 due slide05
9 10/25 Uncertainty:
Decision theory, Bayes rule
Chapter 13, Chapter 14     slide05
9 10/27 Uncertainty: Belief network Chapter 13, Chapter 14     slide05
10 11/1 Planning, Machine Learning Intro Chapter 7.2, 7.7, 10.4.2, 11     slide-planning
slideml3
10 11/3 Advanced topic: Neuroevolution     Program 2 due slide06
11 11/8 Learning: Inductive learning, Decision trees, Perceptrons Chapter 14, Chapter 18     slide07
11 11/10 Learning: Perceptrons, Multilayer networks Chapter 18, Chapter 20 Combined Program 3 / Homework 3 TBA   slide07
12 11/15 Guest Lecture by Dr. Ruihong Huang Natural Language Processing Case Study: IBM Watson     slide-nlp
12 11/17 Learning: Backpropagation Chapter 18, Chapter 20   Program 2 due slide07
13 11/22 Learning: Unsupervised learning, Self-organizing maps Chapter 18, Chapter 20 Combined Homework 3 / Program 3 announced   slide07
13 11/24 Thanksgiving: No class        
14 11/29 Learning: Recurrent networks, Genetic algorithms Chapter 18, Chapter 20     slide07
14 12/1 Advanced topic: Deep learning       slide-dl
15 12/6 Advanced topic: Problem Posing Full slides with animations [pdf]   Combined Program 3 / Homework 3 due slide-probposing
16 12/13Final exam: December 13 (Tuesday): 1-3pm, in ETB 1020 Homework 3/Program 3 due 12/11 11:59pm

IV. Credits

Many ideas and example codes were borrowed from Gordon Novak's AI Course and Risto Miikkulainen's AI Course at the University of Texas at Austin (Course number CS381K).