CSE 537 Artificial Intelligence

The final questions when if solved separately by team members should have a team member written next to
question. EXAMPLE: Q1 - solved by Anita Wasilewska, Q2 - solved by John .. etc.

Please give me
   (1)your 2 questions per team. (Team 25,31)
   (2)First 3 slides in HTML format. (Pure text HTML preferred, due to the space of the server)
   (3) Remarks of other teams. Give me your remarks for every other team. For example, you and your friends are in team 01. Then   you give every other team your remarks just one copy. If you and your friends have different credits for one team, say team 12, choose the mean of the different remarks for team12.

The assess form is an EXCEL format file. CHANGE THE FILE NAME as "yourteam#.xls"
Fill it out and email back in a single mail with the subject "yourteam#_assess" (say,team01_assess).

Click here to see the information of Presentation Timetable.
Click here to see the information of teams' name list.

Click here to see the lecture slides.
Click here to see the information of visitors

Professor Anita Wasilewska E-mail address: anita@cs.sunysb.edu, Office phone number: 632 8458

Office location: Computer Science Department building, office 1428.

Office Hours Tue: 1 - 2 pm, Th: 4 - 5 pm, and by appointment.

Textbook
        1. The Essence of ARTIFICIAL INTELLIGENCE, Alison Cawsey, Prentice HALL, 1998
        2. Rough Sets (Theoretical Aspects of Reasoning about Data), Zdzislaw Pawlak, KLUWER, 1991
        3. Managing Uncertainty in Expert Systems, Jerzy Grzymala-Busse, KLUWER, 1991

REMARK   Pawlak and Busse books are out of print. I will put copies of relevant pages on the web.
         We will follow the PAWLAK book VERY closely! I will also use some parts of BUSSE book. The
         copies of pages are from the original manuscripts and I have permission of the authors. Alison
         Cawsey book is VERY useful. It is a cheap, small, very well written book which covers shortly all
         areas of AI. I will use exercises from her book, and others for your Final examination.

Final Test (100pts)
        There will be an OPEN BOOK, in class Final Test covering the lectures material,
        exercises from course books, and material covered by PRESENTAIONS. It will take place during
        the finals week according to University final exams schedule (not published yet).

Presentations (100pts)
Each team (2-3 students) will have to give ONE LONG (30 -35 minutes) presentation (see description below).

Presentation evaluation   Students will be graded individually for the presentation skills (25pts)
        and as a team for the content, organization, clarity, and amount of work put into research and
        preparation (75pts).

Presentation Report (50pts) Each TEAM has to submit a presentations report (see description below).

Final Paper (50pts) Each TEAM has to submit a final paper (see description below).

Final Grade Computation
During the semester you can earn 300pts or more (in the case of extra points). The grade will be determined in the following way: # of earned points divided by 3 = % grade.
The % grade which is translated into 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%.

Why Presentation?
        1. AI is a VERY large field and you come to AI class usually with your own interest - so I give you a chance to EXPLORE and share with us your own interest and expertise!
        2. I can't teach you ALL of AI, so your presentations make the course more versatile, and hence more interesting.
        3. They are to your future ADVANTAGE. In modern world you have to be a GOOD PRESENTER - I give you an opportunity to become a better one. I will judge you on the content of your presentation, your understanding of presented material and the presentation form.

Presentation Book
Use Alison Cawsey book when you prepare your presentation. The book is a short overview of all fields of AI. Make one or two relevant slides from the information included in the book.

Presentation Types
        There will be two types of presentations.
        Applications    I want you to search a WEB for interesting APPLICATIONS in the domain of AI of your choice. It can be scientific or commercial. You don't need to understand depth WHY the technique (application) work and what REALLY is involved (very often it is a secret anyway!), but TRY to figure out at least by the name - check with your book. Search the Web, find something what you think INTERESTING and present it to us and explain why you find it interesting.
        Technical    This is a more technical presentation of METHODS, techniques, algorithms in the AI domain of your choice. I have some materials and subjects (see list of technical subjects) but please feel free to come up with your own subject that YOU are especially interested in. Learn it, think about it and teach it to us.

TEAMS All presentations are given by teams. You (the team) decide which members of the team is doing which part: technical or application.

Remark I have listed some subjects (see the course content below) but please feel free to come up with your own subject that YOU are especially interested in. Let me know what it is and then learn it, think about it and teach it to us.

Presentation General Principles
First slide must contain your names, student IDs and course number and the title. Second slide must contain ALL sources you used for the LECTURE part of your presentation. The book is included. In the case of the book the reference you have to put are title of the chapter, sections and pages numbers. Third slide is an OVERVIEW of your presentation. Fourth slide include the title and references of your research paper presented. You have to e-mail (as a text file) these four slides to the TA in order to put it on the WEB. ALSO remember- give a source of any PICTURE or any DIRECT citation on the bottom of each of your SLIDES where it appears. If slides miss citations I will subtract points while evaluating your presentation.

Presentation Teams
Students work in 2 - 3 people teams. For example: one persons does a theoretical presentation of a method or algorithm (one part of the presentation), or research paper in chosen domain of AI and one or two others present applications of that domain (algorithm) as the second
part of the presentation. If you decide to have one presentation for two people it has to be twice as long and both presenters have to spent the same amount of time presenting.

PRESENTATIONS: General Remark : Students presentations ARE AN INTEGRAL PART of
        the course. Listen to them, take notes, ask questions. Remember that I will include questions
        FROM presentations on your FINAL examination. Final is an open book test, so you will be able
        to look at your notes!

Encouragement for Presentations
        Here is a part of an e-mail from my previous student:
        I just want to say "Thank you, Professor" for you great efforts. You have taught us many things, you have given a lot of care to us and you have been generous and reasonable. How can anyone ask more?
        I learned a very very important thing through AI presentation. I learned a lot from my classmates and from you. I learned a lot from both excellent ones and not so good ones. Especially, I was very happy when I gave my presentation. You instruct me how to talk and behave. At first, I was very nervous but I received courage from you so I could do it well.

Presentation Report (50pts) (Team Work)
         Classroom attendence is essential to the understanding of other students presentations. You are
         graduate students, so I will not insult you by taking the attendence. BUT I want each team
         to submitt a written REPORT about choosen 10 presentations. The report must contain: 1.
         motivation WHY you chose those presentations for the report, 2. One page description-summary
        (own words!) of each presentation, 3. Your own evaluation of the presenatation: the content and
        the way it was presented.

        I will provide evaluations forms.

Final Paper (50pts)
        Here is the procedure:
        Step 1    Find (Web or other sources) a research paper on an AI subject of your choice.
        Step 2    Write motivation why you have chosen this particular paper.
        Step 3    Write at least one page summary of the paper. You have to state if it is an application or theoretical paper and what is the real point of the paper. It has to be your own summary, not the author's. You have to specify which techniques, algorithms, are used or improved upon etc...
        Step 4    Write your own evaluation of the paper. Address the following:
            1. Does the author(s) really accomplished what they said they did?
            2. How important is the result - based on what you KNOW (after our course!) about the field.
            3. How well the paper is written: motivation, description of related research, statement of the problem of the paper, its history and relevance to the field.
            4. How important is the paper with respect of future development of the field: does it open new directions, or in a case of general model building paper, how much of the past research does it cover.
            5. Any other remarks and your own reflections.

FINAL Paper General Principle
Any direct citations (even of ONE SENTENCE!) must have a standard form of a citation: give the page of the paper and show clearly when it start and when it finishes.

Tuesdays
My Lectures plus ONE student presentation. Lectures: Overview of AI - methods and fields (little book), Theory and Applications of ROUGH SETS, Inductive Machine Learning.

Lecture Introduction. It should not take longer then a week. We use the ”little ” book The Essence of
ARTIFICIAL INTELLIGENCE, by Alison Cawsey. Buy it! It is good, short and non expensive. It
is a good introduction and overview of history and major areas of AI. My slides (of course) contain
a little more materials on some subjects and a little less on other subjects. In particular we will
cover:
Lecture AI history and applications.

Lecture Knowledge Representation- Propositional and Predicate Calculus.

Presentations Rough set algorithms and applicatioms.
STUDENTS theoretical and applications presentations.

Presentations Robotics, Intelligent robots.
STUDENTS theoretical and applications presentations.

Presentations Machine Learning and evolutionary computing. Neural Network and Genetic Algo-rithms.
STUDENTS theoretical and applications presentations.

Presentations Biometrics.
STUDENTS theoretical and applications presentations.

Presentations Quantum Computing.
STUDENTS theoretical and applications presentations.

Presentations Natural Language processing - basic techniques.
STUDENTS theoretical and applications presentations.

Presentations Intelligent Visualisation.
STUDENTS theoretical and applications presentations.

Presentations Intelligent web agents.
STUDENTS theoretical and applications presentations.

Presentations Games and intelligent games
STUDENTS theoretical and applications presentations.