CSE352
ARTIFICIAL INTELLIGENCE
FALL 2017



Course Information

News:

Midterm 1 is coming: October 25

Midterm covers   Lectures 1- 8 and Hmk1, Hmk2

Homework 2 is due  October 18

Homework 1 Solutions and Teams grades posted

New Lectures 8 and 9 posted

  

Extra help with LOGIC part:
  • ADAM CATTO
  • e-mail: adam.catto@stonybrook.edu
  • Office hours: TUESDAY 2:00 - 3:30 pm
  • EXTRA HOURS: Tuesdays and Wednesdays 8:45am - 10:45 am
  • Office Location: Old Computer Science building room 2203

  • Please send all e-mail concerning Research Presentations and TEAMS formation to TA. 

    Time:  Monday,  Wednesday     2:30 - 3:50 pm

    Place: JAVITS 109

     Professor:   Anita Wasilewska

    208 NCS Building
    Phone: 632-8458
    e-mail: anitaatcs.stonybrook.edu 

    Office Hours:
    Monday, Wednesday at 1:15 pm - 2:00 pm,  4:15pm- 5pm,  and  by appointment

    Teaching Assistant


  • Mohaddeseh Bastan
  • TA e-mail:  mbastan@cs.stonybrook.edu 
  • PLEASE write cse352 in the SUBJECT so she/he can recognize course e-mails
  • Office hours:  Monday 6:00pm - 7:30pm, and by appointment
  • Office Location: Old Computer Science building room 2203

  • TA KEEPS all students records; contact TA when you have questions about your records

  • General Course Description

    Artificial Intelligence is a broad and well established field and AI textbooks seem to be getting longer and longer and and often narrowly specialized. Our course attempts t to provide a concise and accessible introduction to the field. It is designed to give a broad, yet in-depth overview of different fields of AI. We will examine the most recognized techniques and algorithms in a rigorous detail. We will also explore trends, areas, and developments of the field in form of students' Research Presentations based on newest research and applications.

    Main Book

    The Essence of Artificial Intelligence
    Allison Cawsey
    Prentice Hall, 1998


    This is a short condensed book (not expensive!) and not very technical.
    We will cover in detail first 3 chapters (plus my lecture notes for technical details) and chapter 7
    Course LECTURE NOTES posted in Downloads EXTEND  the material from the book providing TECHNICAL details and are the MAJOR SOURCE for the course.

    Additional Book:

    DATA MINING Concepts and Techniques
    Jiawei Han, Micheline Kamber
    Morgan Kaufman Publishers, 2003, 2011


    The course outcomes and catalog description are in the offici course description page

    Student Information

    Students ATTENDANCE is the most important, as Lecture Notes serve as an extra textbook for the course and students presentations are integral and as important part of the course design as Professor's lecture.

     I will check class attendance by giving and collecting answers (almost each class) to small questions connected with the lecture; you will get 1-2 extra credit points for your answers

    AI talks in the Department

  • tba
  • GRADING

  • During the semester you have to complete the following
  • Four Homework Assignments -10 pts each - TOTAL 40pts
  • Research Presentation - 40pts - see Presentation  section below and Presentation Description in the Syllabus
  • Students' presentations Evaluati Report - 20pts
  • Project (it is application project- not programming)  - 40 pts - see the section PROJECT below and Project Description in the Syllabus
  • TWO Midterm Tests  80 pts each = 160pts given in class
  • Extra Credit: I will give during the class small questions for extra credit and assign some extra credit work
  • You can earn up to 20 pts of extra credit points during the semester
  • Final Grade Computation

  • NONE OF THE GRADES WILL BE CURVED
  • During the semester you can earn 300pts plus extra credit pts
  • The grade will be determined in the following way: number of earned points divided by 3 = % grade
  • The % grade is translated into a letter grade in a standard way  i.e.
  • 100 - 90 % is A range, 89 - 80 % is B range,
  • 79 - 70 % is C range, 69 - 60 % is D range, and F is below 60%.
  • Details included in the Syllabus
    See course SYLLABUS for details
  • Homework and Test Schedule

  • It is a preliminary schedule; changes, if needed will be advertised in this section

  • Homework 1 is due Wednesday, September 27
  • Homework 2 is due Wednesday, October 18
  • Homework 3 is due Monday, November 16
  • Homework 4 is due Monday, November 27


  • Project Homework YOUR PROJECT DATA (10 extra points) is due Monday, November 27 via e-mail to TA

  • Midterm 1 will be given on Wednesday, October 25

  • Midterm 2 will be given on Wednesday, November 29
  • Students Presentations

    Check "Possible Presentations Subjects" in the Syllabus to get an idea of the subjects to choose from.
    READ Syllabus for detailed description of format, content etc of the Presentations.
    Please mail the TA the number of members in the group, the name, e-mails and the SB ID of each group member, along with the possible  subject of the presentation.
    You CAN change the subject later
    We will try to coordinate subject choices
    Student CAN present the same subject but in this case MUST collaborate
    You can use any sources but use the terminology developed in Professor Lecture Notes and in both Books

    Students Presentations Teams

  • Each TEAM has to deliver a 20 minutes long presentation on a chosen topic of AI as a member of a chosen Presentation Team of three or four students
  • It is students responsibility to form the Presentation Teams
  • Each team has to have a designated Team Leader in order to communicate with Professor and the course TA
  • Please e-mail TA as soon as possible, and the latest by SEPTEMBER 20  the following:
  • names and e-mails of your Team members denoting who is the designated Team Leader
  • e-mail TA and Professor a TITLE and a one short paragraph long description of your team presentation;
  • you can CHANGE the subject  later, if needed
  • TA will assign a Team Number to each team and e- mail it to each  Team Leader   to be used for future correspondence
  • You have to use your Team Number when reserving the presentation date; you don't need the TITLE to reserve the  presentation day
  • RESERVE the Presentation Date via e-mail to TA as soon as possible; "first come first serve"
  • YOU CAN SUBMIT your HOMEWORK as a TEAM

    PRESENTATIONS SCHEDULE

  • D1: Monday, October 23

  • Team 5: AI in Games
    Team 6: AI Application in Genetic Algorithm
    Team 13: AI in Board Games

  • D2:  October 30

  • Team 1: AI Applications to Finance
    Team 2: AI Applications to Music
    Team 15: AI and Neural Networks

  • D3: Monday, November 6

  • Team 3: AI in Video Games
      Team 14: AI in Self-driving Cars
      Team16: AI in Pattern Recognition
     


  • D4  Wednesday, November 15
  •    Team 12:   AI Application in Music 
       Team 11: AI for Children
        Team 9: AI in Facial Recognition


  • D5    Monday, November 27
  •   

       Team 4:  AI in Video Games
       Team 7:  AI Applications in NLP
        Team 8: AI in Intelligent Assistants
        
  • Midterm 1:  October 25

  • Midterm 2: November 29

  •  
  • Thanksgiving Break: November 22 - 26

  • PROJECT Presentation:  December 4, 6

  • Students' Presentations Evaluation Report:

    Download a pdf of the report form from Presentation Report

    Project Data

  • Play around with the data and familiarize yourself with it (DOWNLOAD: bakarydata.xls )

    Project Description

    Project Description
    Project Homework

    Project Tools

    WEKA
    RapidMiner

    Past Project Examples

    Example 1
    Example 2
    Example 3

    DOWNLOADS

    Syllabus 
    Course Syllabus Slides

    Chapter: Introduction to Classical Logic for Hmk 1
    BUSSE HANDOUT for Hmk 1
    Decision Tree and NN Algorithms HANDOUT

    HOMEWORKS: 10pts each

    Homework 1
    Homework 2
    Homework 3
    Homework 4

    Homeworks Solutions


    Homework 1 Solutions
    Homework 1 Teams Grades
    Homework 2 Solutions to be posted
    Homework 3 Solutions to be posted

    Past Students Presentations


     Example:
    Pattern Recognition

    Sci-Fic Film Short Circuit
    Google Deep Dream

    AI in Voice and Image Recognition
    Self Driving Cars

    AI History
    AI in Games
    Sound Recognition

    AI in Computer Vision; Past, Present and Future
    Genetic Algorithms
    Computer Vision and Facial Recognision

    Lecture Notes:


    Lecture 1: Chapter 1; Introduction to AI
    Lecture 2: Chapter 2; Knowledge Representation
    Lecture 3: Chapter 2; Predicate Logic Part 1
    Lecture 4: Chapters 2, 3, 4, Busse Notes: Rule Based Systems
    Lecture 5a: REVIEW for Hmk 1
    Lecture 5b: LOGIC REVIEW
    Lecture 6: Chapter 7; Introduction to Learning
    Lecture 7: Classification, Part 1: Introduction
    Lecture 7: Classification Part 2: Testing Classifier Accuracy
    Lecture 8: Decision Tree BASIC Algoirithm, Examples
    Lecture 9: Preprocessing
    Lecture 10: Decision Tree Full Algorithm
    Lecture 11: Neural Networks
    Lecture 12: Classification Review
    Lecture13: Association- Apriori Algorithm
    Lecture14: Classification by Association
    Lecture 15: Genetic Algorithms
    Lecture 16: Genetic Algorithms Examples
    Lecture 17: Clustering
      Lecture 18: Bayesian Classification
      Resolution, Part 1, Handout 4
      Lecture 19: Resolution Strategies, Part 2
    Lecture 20: Resolution Strategies, Part 3
    Lecture 21: Predicate Logic, Part 2

    ACADEMIC INTEGRITY STATEMENT

    Each student must pursue his or her academic goals honestly and be personally accountable for all submitted work. Representing another person's work as your own is always wrong. Any suspected instance of academic dishonesty will be reported to the Academic Judiciary. For more comprehensive information on academic integrity, including categories of academic dishonesty, please refer to the academic judiciary website at Academic Judiciary Website

    Stony Brook University Syllabus Statement

    If you have a physical, psychological, medical, or learning disability that may impact your course work, please contact Disability Support Services at (631) 632-6748 or Disability Support ServicesWebsite They will determine with you what accommodations are necessary and appropriate. All information and documentation is confidential. Students who require assistance during emergency evacuation are encouraged to discuss their needs with their professors and Disability Support Services. For procedures and information go to the following website: Disability Support Services Website