CSCE 625-600 AI:
Spring 2020

Syllabus

NEWS: 4/21/20, 06:44PM (Tue)
  • [04/21/20] Last day to Q-drop is 4/24 Friday!
  • [04/20/20] Final exam will be given on eCampus during the official TAMU final exam period. Proctoring will be done through zoom (with camera on).
  • [04/16/20] slide-keras-tf uploaded.
  • [04/15/20] slide09-overcoming uploaded.
  • [04/13/20] slide08-deeplearning uploaded.
  • [04/09/20] Practice exam uploaded to eCampus (for the final exam).
  • [04/06/20] slide07-neuroevol uploaded.
  • [04/02/20] Homework 4 + program 3 uploaded to eCampus. Due 4/25 Sat.
  • [03/26/20] Zoom lectures now available on eCampus, in Course Materials, Video Catalog.
  • [03/26/20] Program 2 extension: due 3/28 Saturday 11:59pm.
  • [03/16/20] slide06 uploaded.
  • [03/12/20] Class canceled until 3/20 due to COVID-19. Program 2 due date extended to 3/26 (Thu).
  • [03/05/20] slideml3 uploaded.
  • [03/05/20] slide-planning uploaded.
  • [02/28/20] Unification in JAVA -- for those writing code in non-LISP languages.
  • [02/27/20] Program 2 uploaded to eCampus.
  • [02/25/20] slide05 uploaded.
  • [02/20/20] Midterm materials will be up to and including propostional logic. There will be no coding/LISP problems in the exam.
  • [02/18/20] Homework 1 solution posted on eCampus.
  • [02/18/20] Homework 3 posted on eCampus.
  • [02/13/20] Program 1 due date postponed to Monday 2/17.
  • [02/13/20] Program 1 clarification: (1) report file should include your experiment results (# nodes visited, max node list size, etc. for different algorithms and different tasks [easy, medium, hard]) and analysis, as detailed in page 5. (2) result file should include the input and the output dump from your program.
  • [02/11/20] Homework 2 uploaded to eCampus.
  • [02/10/20] Program 1 clarification: The goal is '(1 2 3 8 0 4 7 6 5). Otherwise, the Easy, Medium, Hard may not make sense.
  • [02/09/20] Alpha beta pruning example uploaded to the board.
  • [02/06/20] Homework 1 tips uploaded to the board.
  • [02/05/20] LISP compiling tip uploaded to the board.
  • [02/01/20] slide04 uploaded.
  • [01/29/20] Program 1 uploaded to eCampus. ** Important note: The operator ordering should be UP DOWN LEFT RIGHT (for uninformed searches) **
  • [01/28/20] Attendance survey uploaded to eCampus (due 2/1).
  • [01/28/20] Homework 1 uploaded to eCampus.
  • [01/23/20] Slide03 uploaded, and Program 0: LISP exercise uploaded to eCampus.
  • [01/21/20] LISP resources posted on the board
  • [01/17/20] Are your students bored? This AI could tell you!: article from IEEE Spectrum. :-)
  • [01/16/20] Full page slides are avaliable as http://faculty.cs.tamu.edu/choe/625-slide01.pdf, etc.
  • [01/14/20] Prerequisit fixed: CSCE 331->221.
  • [01/14/20] Alan Turing's Computing Machinery and Intelligence (1950).
  • [01/14/20] Course web site goes online!
Read-Only Bulletin Board.: 1/12/20, 12:59PM (Sun)

Page last modified: 4/21/20, 06:45PM Tuesday.

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

I. General Information

Grader:

Ji Su Byun
Email: jb733 (a) tamu.edu
* Grader does not hold office hours.

Instructor:

Dr. Yoonsuck Choe
Email: choe@tamu.edu
Office: HRBB 322B
Phone: 979-845-5466
Hours: Tue/Thu 11:00pm-12:00pm (2020 Spring)

Prerequisite/Restrictions:

CSCE 221 (Data Structures and Algorithms) or equivalent.

Lectures:

Tue/Thu 2:20pm-3:35pm, ZACH 350 (2020 Spring)

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
Note: The 4th edition is coming soon, but it will not be out until later in this semester, so we will have to stick with the 3rd edition.

Henry Brighton and Howard Selina, Introducing Artificial Intelligence: A Graphic Guide, Icon Books, 2010.
Book web page

Note: Earlier print of this book under the title "Introducing Artificial Intelligence" is the same in its content. Original publishing year is 2003.

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 (including DeepLearning)

Grading:

  1. Exams: 50% (midterm: 20%, final: 30%)
    Make up exams:
    • Only cases allowed under "Excused Absences" under TAMU Student Rules, Rule 7. Attendance will be eligible for make up exams. See 7.2 Absences and 7.3 Absence Documentation and Verification. Please read this very carefully. (For example, non-acute medical service does not constitute an excused absence, and it is the student's responsibility to provide documentation substantiating the reason for absence.)
    • There will be no make up exam for those who do not show up for the exam without prior notice.
    • Make up exams will be different from the original exams although the difficuly will be adjusted to be comparable.
    Exam rules
    • All exams will be closed book. Put all books, notes (exception below), cell phones, calculators, or any information containing media in your bag.
    • You may bring a 1-sheet hand-written note (US letter paper; you can use both sides). Write your full name on the top left corner of page 1. A4 or any other sized paper, two pages glued together, photocopied or printed notes, name not written or not written in the exact location specified are all in violation of this rule, and this will result in a 10-point penalty.
    • (Depending on the classroom) If you're right handed, sit in a right-handed seat. If you're left handed, sit in a left-handed seat.
    • Bring your student ID or Texas driver's license. You will not allowed to take the exam without an ID.
    • Aggie honor code will be strictly enforced.
  2. Homeworks: 20% (about 4, 5% each)
  3. Programming Assignments: 30% (about 3: 10% each)
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'.

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:

Texas A&M University is committed to providing equitable access to learning opportunities for all students. If you experience barriers to your education due to a disability or think you may have a disability, please contact Disability Resources in the Student Services Building or at (979) 845-1637 or visit http://disability.tamu.edu. Disabilities may include, but are not limited to attentional, learning, mental health, sensory, physical, or chronic health conditions. All students are encouraged to discuss their disability related needs with Disability Resources and their instructors as soon as possible.

II. Resources

  1. CMU Common Lisp (This one will be used in the class.)

III. Weekly Schedule and Class Notes

Week
Date
Topic
Reading
Assignments
Notices and Dues
Notes
1 1/14 Introduction Chapter 1   First day of class slide01.pdf
1 1/16 Introduction
LISP
Chapter 26
26.1 and 26.2
  1/17: Last day to add/drop slide01.pdf
slide02.pdf
2 1/21 Symbolic Differentiation       slide02.pdf
2 1/23 Uninformed Search (BFS,DFS,DLS,IDS) Chapter 3.1-3.6     slide03.pdf
3 1/28 Informed Search (BestFS,Greedy,A*) Chapter 4.1-4.3 (4.4 optional) Homework 1: Search
See eCampus.
  slide03.pdf
3 1/30 IDA*,Heuristic Search,
Simulated Annealing, Constraint Satisfaction, etc.
Chapter 4, Chapter 6.1 Program 1: Search and Game Playing   slide03.pdf
4 2/4 Game playing
Min-Max, Alpha-Beta
Chapter 5     slide03.pdf
4 2/6 Game playing wrap up;
Representation, logic, frames
Chapter 5
Chapter 7
Homework 2: Game Playing / Propositional Logic Homework 1 due (2/8 Sat) slide03.pdf
slide04.pdf
5 2/11 TBA        
5 2/13 Propositional Logic Chapter 7   Program 1 due (2/15 Sat 2/17 Mon) slide04.pdf
6 2/18 Theorem proving
First order logic (FOL)
Chapter 8; Chapter 9 Homework 3: First-order Logic   slide04.pdf
6 2/20 Theorem proving
for FOL
Chapter 8; Chapter 9   Homework 2 due (2/22 Sat) slide04.pdf
7 2/25 Midterm Exam In class   3/2: Mid-semester Grades due  
7 2/27 Inference
for FOL
Chapter 9 Program 2: Theorem Prover   slide04.pdf
8 3/3 Uncertainty Chapter 13   Homework 3 due slide05.pdf
8 3/5 Uncertainty:
Decision theory, Bayes rule
Chapter 13, Chapter 14     slide05.pdf
9 3/10 Spring Break: 3/9-3/13        
9 3/12 Spring Break: 3/9-3/13        
10 3/17 [Class cancelled] Topic to discussed next week : Uncertainty: Belief network Chapter 13, Chapter 14     slide05.pdf
10 3/19 [Class cancelled] Topic to discussed next week : Planning, Machine Learning Intro Chapter 7.2, 7.7, 10.4.2, 11   Program 2 due (3/18 Wed) slide-planning.pdf
slideml3.pdf
11 3/24 Plannning ; ML Intro ; Learning: Inductive learning, Decision trees, Perceptrons Chapter 14, Chapter 18     slide-planning.pdf
slideml3.pdf
slide06.pdf
11 3/26 Learning: Perceptrons, Multilayer networks Chapter 18, Chapter 20 Combined Homework 4 / Program 3: Uncertainty, Probabilistic Reasoning, Learning Program 2 due (3/26 Thu 3/28 Saturday) slideml3.pdf
slide06.pdf
12 3/31 Learning: Backpropagation Chapter 18, Chapter 20     slide06.pdf
12 4/2 Learning: Unsupervised learning, Self-organizing maps Chapter 18, Chapter 20 Combined Homework 4 / Program 3 TBA: Uncertainty, Probabilistic Reasoning, Learning   slide06.pdf
13 4/7 Learning: Recurrent networks, Genetic algorithms Chapter 18, Chapter 20     slide06.pdf
13 4/9 Advanced topic: Neuroevolution       slide07-neuroevol.pdf
14 4/14 Advanced topic: Deep learning     Last day to Q-drop (4/14) slide08-deeplearning.pdf
14 4/16 Advanced topic: Deep learning     Combined Homework 4 / Program 3 due slide08-deeplearning.pdf
slide-keras-tf.pdf
15 4/21 Advanced topic: Overcoming limitations of deep learning       slide09-overcoming.pdf
15 4/23 [Last day of class: 4/23] Advanced topic: Overcoming limitations of deep learning     Combined Homework 4 / Program 3 due 4/25 Sat; PICA evaluation ends 4/29; Last day to Q-drop (4/24) slide09-overcoming.pdf
16 5/5(Tuesday) Final exam: May 5 (Tuesday): 1-3pm, on eCampus Degree candidate grades due 5/6

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).