CSE 471: Introduction to Artificial Intelligence

Fall 2018

01:30 pm - 02:45 pm Tuesdays and Thursdays | LL2

Instructor

Prof. Siddharth Srivastava

Office Hours 09:00 am - 10:00 am Tuesdays and Thursdays | BYENG 592

Contact Details siddharths@asu.edu | BYENG 592

Teaching Assistant

Kislay Kumar

TA Office Hours 11:00 am - 12:00 noon Mondays and Wednesdays | BYENG 221 (CIDSE TA Lab)

TA Contact Details kkumar28@asu.edu

Graders

Chirav Dave (cdave1@asu.edu)

Midhun P Madhusoodanan (mpookkot@asu.edu)

Overview

This course introduces you to Artificial Intelligence and covers basic ideas and methods in AI. Students will learn about informed and uninformed search, probabilistic inference, Markov decision processes, reinforcement learning, statistical learning and modeling and representation of problems.

Tentative Schedule

Lecture Number	Date	Topic(s)	Prior Reading	Assignments
1	Thu Aug 16	Intro, Rational Agents, Markov Models	Textbook 1.1-1.5, 2.1,2.2	Released: Project 0:Python Basics
2	Tue Aug 21	Environment Types	Textbook 2.3-2.5
3	Thu Aug 23	Search: Uninformed	Textbook 3.1-3.4
4	Tue Aug 28	Search: Informed	Textbook 3.5-3.7	Released: Project 1: Search, HW 1; Due: Project 0
5	Thu Aug 30	Constraint Satisfaction Problems
6	Tue Sep 4	Representation and Modeling 1	Textbook 7.1-7.8, 8.1-8.5
7	Thu Sep 6	Deterministic Planning	Textbook 10.1-10.3, 11.1-11.2
8	Tue Sep 11	Partial Observability and Stochasticity in Planning, Probability	Textbook 11.3-11.5, 13.1-13.5	Released: Project 2: Planning, HW 2; Due: Project 1, HW 1
9	Thu Sep 13	Bayesian Networks 1	Textbook 14.1-14.8
10	Tue Sep 18	Bayesian Networks 2	Textbook 14.1-14.8
11	Thu Sep 20	Bayesian Networks 3	Textbook 14.1-14.8
12	Tue Sep 25	Bayesian Networks 4	Textbook 14.1-14.8	Released: Project 3: Ghostbuster, HW 3; Due: Project 2, HW 2
13	Thu Sep 27	Hidden Markov Models 1	Textbook 15.1-15.4
14	Tue Oct 2	Markov Decision Processes 1	Textbook 17.1-17.3
15	Thu Oct 4	Markov Decision Processes 2	Textbook 17.1-17.3
16	Thu Oct 11	MIDTERM
17	Tue Oct 16	Representation and Modelling 2		Due: Project 3, HW 3
18	Thu Oct 18	Markov Decision Processes 3	Textbook 17.1-17.3	Released: Project 4: Reinforcement Learning, HW 4
19	Tue Oct 23	Reinforcement Learning 1	Textbook 21.1-21.7
20	Thu Oct 25	Reinforcement Learning 2	Textbook 21.1-21.7
21	Tue Oct 30	Partially Observable Markov Decision Process	Textbook 17.4
22	Thu Nov 1	Game Trees 1	Textbook 5.1-5.9	Released: Project 5: Multiagent Search, HW 5; Due: Project 4, HW 4 on Nov 2nd
23	Tue Nov 6	Game Trees 2	Textbook 5.1-5.9
24	Thu Nov 8	Statistical Learning, Naïve Bayes	Textbook 20.1-20.2
25	Tue Nov 13	Neural Networks	Textbook 18.7	Released: Project 6: Classification, HW 6; Due: Project 5, HW 5
26	Thu Nov 15	Neural Networks for Sequential Decision Making	Papers: Deep Q Network
27	Tue Nov 20	Robotics 1	Textbook 25.1-25.9
28	Tue Nov 27	Robotics 2	Textbook 25.1-25.9	Due: Project 6, HW 6
29	Thu Nov 29	Review

Note: Final Exam will be on University's pre defined examination dates. Please check University Exam Calendar for more details

Course format

There will be regular meetings on Tuesdays and Thursdays (unless stated otherwise) covering fundamentals of AI. Programming assignments will be released bi-weekly. Homeworks will be assigned bi-weekly. Homeworks must be typeset using word processing software (E.g. Word or equivalent) and submitted before the due date indicated on the homework.
There will be no groups for programming assignments and homeworks. Each student is required to submit their own work through canvas. Do not try to gain credit for someone else’s work.

Note: Do not submit a scanned copy of the homework. Acceptable formats are: doc, docx or pdf.

Grading

Programming Assignments: 30%
Homeworks: 30%
Midterm Exam: 15%
Final Exam: 23%
Class Participation: 2%

Grading Scale*

A+: > 95
A : 90-95
A-: 85-90
B+: 80-85
B : 75-80
B-: 65-75
C+: 60-65
C : 50-60
D : 40-50
E : <40
*The instructor reserves the right to normalize and scale grades

Prerequisites

CSE 310
Proficiency with the Python programming language.

Resources

Textbook Artificial Intelligence: A Modern Approach, 3rd Edition by Stuart Russell and Peter Norvig
Online Discussion and Polls: Canvas course page.

Absence and Make-up Policies

If a student is unable to take up the mid-term or final exam due to unavoidable circumstances, it is the student’s responsibility to notify the instructor beforehand to make necessary accommodations, if possible. Students are advised to notify the instructor as early as possible. Students who expect to miss class due to officially university-sanctioned activities should inform the instructor early in the semester. Alternative arrangements will generally be made for any examinations and other graded in-class work affected by such absences. Absences not noted at the beginning of class will be considered only with a note from a reliable third-party (e.g., a doctor).

The preceding policies are based on ACD 304–04, “Accommodation for Religious Practices” and ACD 304–02, “Missed Classes Due to University-Sanctioned Activities.”

Classroom Behavior

Cell phones and pagers must be turned off during class to avoid causing distractions, unless instructed by the presenters (e.g., for online polling software). The use of recording devices is not permitted during class. Any violent or threatening conduct by an ASU student in this class will be reported to the ASU Police Department and the Office of the Dean of Students.

Academic Integrity

All students in this class are subject to ASU’s Academic Integrity Policy (available at http://provost.asu.edu/academicintegrity) and should acquaint themselves with its content and requirements, including a strict prohibition against plagiarism.

On first detection of cheating, student(s) shall get:

Zero points for that quiz/assignment/exam
Grade scales down; max becomes C for all students involved
If you would have received a C without that quiz/assignment/exam, now you get a D
To get a C you need to score at the level of A or above in the rest of the course

Second detection:

Report to Dean’s office
Grade X

All violations will be reported to the Dean’s office, who maintain records of all offenses. Students are expected to abide by the FSE Honor Code (http://engineering.asu.edu/integrity/)

Disability Accommodations

Suitable accommodations will be made for students having disabilities and students should notify the instructor as early as possible if they will require same. Such students must be registered with the Disability Resource Center and provide documentation to that effect.

Sexual Discrimination

Title IX is a federal law that provides that no person be excluded on the basis of sex from participation in, be denied benefits of, or be subjected to discrimination under any education program or activity. Both Title IX and university policy make clear that sexual violence and harassment based on sex is prohibited. An individual who believes they have been subjected to sexual violence or harassed on the basis of sex can seek support, including counseling and academic support, from the university. If you or someone you know has been harassed on the basis of sex or sexually assaulted, you can find information and resources at https://sexualviolenceprevention.asu.edu/faqs.
As a mandated reporter, I am obligated to report any information I become aware of regarding alleged acts of sexual discrimination, including sexual violence and dating violence. ASU Counseling Services, https://eoss.asu.edu/counseling, is available if you wish discuss any concerns confidentially and privately.

Notice: Any information in this syllabus (other than grading and absence policies) may be subject to change with reasonable advance notice.

Notice: All contents of these lectures, including written materials distributed to the class, are under copyright protection. Notes based on these materials may not be sold or commercialized without the express permission of the instructor. [Note: Based on ACD 304-06.]