Artificial Intelligence 2012
Prabhas Chongstitvatana
email prabhas at chula dot ac dot th
Course Description
Foundations of artificial intelligence, solving problems by
searching, knowledge representation, first-order logic, inference in
first-order logic, language processing, machine learning.
Previous lecture 2011
Announcement
26 Sept 2012 Fan page is open at http://www.facebook.com/AiClassMahidol2012
30 Oct 2012 Mid term exam will be given on 6 Nov 2012, 1:15 - 2:15 pm
in class
1 Nov 2012 My lecture is updated Philosophy
of AI AI as search
20 Nov 2012 lecture note: Natural language
Top-down parser
21 Nov 2012 Final exam is on 11 Dec 2012, 2-4pm. lecture note Recursive
programming with List
28 Nov 2012 Lecture on Genetic
Algorithms
Lecture
1) Structure of Intelligent Agents Introduction
(aima) Intelligent Agent (aima)
Philosophy of AI
2) Solving Problems by Searching Boonserm
slide 1 AI as search
3) Representation, Reasoning, and Logic Boonserm
slide 3
4) First-Order Logic
5) Language processing Boonserm slide 4
(NLP) Natural language Top-down
parser
6) Speech Recognition
7) Machine Learning Boonserm slide 5 (ML)
8) Computing by evolution Genetic Algorithms
9) Neural Networks Nervous
system
Final examination
Homework
26 Sept 2012 Read and prepare to discuss a philosophical issue in AI,
"Can machines really think?" Chinese
Room Argument
9 Oct 2012 Complete your State-Space drawing of 15-puzzle, labelling it
with values from your heuristic functions.
23 Oct 2012 Try out my puzzle.c
Arrange your tool to compile and run it. The give source does blind search
with Depth-First-Search. Try to make it Breadth-First-Search. Run both
versions and observe the difference in terms of the number of nodes explored
and the quality of solutions (the number of move to solve the problem).
30 Oct 2012 Prepare for your midterm. At most four questions will be
presented.
13 Nov 2012 Write a naive top-down parser. Use any language that you are
comfortable with. See if it can parse the examples in class.
27 Nov 2012 Try applet of GA. Run several examples to get the feeling how
GA solve these problems and how to set up parameters.
Assessment
Final exam 30 %
Midterm exam 20 %
Class work 30 %
Assignments 20 %
Total 100 %
Reference Text
1) This one is a standard AI text used in US.
Stuart Russell, Peter Norvig, "Artificial Intelligence: A Modern
Approach," Prentice Hall, 2010
link to textbook website http://aima.cs.berkeley.edu/

2) If you want to "program" for AI, this one is a must:
Paradigms of Artificial Intelligence Programming: Case Studies in Common
Lisp by Peter Norvig (1991) ISBN-10: 1558601910

3) Boonserm Kijsirikul, "Artificial Intelligence" in Thai, Department of
computer engineering, Chulalongkorn University (free
download here)
4) other AI related free e-book (search on 26 Sept 2012) http://www.e-booksdirectory.com/listing.php?category=28
Additional materials
video of Watson at Jeopardy http://www.youtube.com/watch?v=WFR3lOm_xhE
Example: Video
of a biped robot walking using Evolutionary Algorithm. from the
paper: Chaisukkosol, C. and Chongstitvatana, P., "Evolving control
programs for a biped static walker", IEEE Inter. Conf. on Humanoid Robots,
Waseda, Tokyo, November 22-24, 2001. full
paper
Famous historical AI program : eliza
Artificial Neural Network Simulator http://www.ra.cs.uni-tuebingen.de/SNNS/
http://neuroph.sourceforge.net/index.html
Application of AI, Data Mining: Using WEKA video (20 min) http://www.youtube.com/watch?v=m7kpIBGEdkI
Applet
(animation) for GA
http://www.rennard.org/alife/english/gavgb.html
Genetic
Algorithm Viewer 1.0 is a demonstration applet of the functioning of a
Genetic Algorithm (GA). It aims at showing the power of GA and of the main
mechanisms used while permitting a certain form of visualization of the
general functioning.
http://www.ads.tuwien.ac.at/raidl/tspga/TSPGA.html
Visualisation of Genetic Algorithms for the Traveling Salesman Problem in
Java
http://www.stellaralchemy.com/ice/
The applet executes what is called a genetic algorithm (GA). To facilitate
understanding, every step in the GA is animated. This particular GA
evolves solutions to a simple board game. This program also detects and
reports if any irreducibly complex (IC) solutions arise during the
evolution of its population of solutions to the board game.
http://www.obitko.com/tutorials/genetic-algorithms/example-function-minimum.php
Minimum of Function: The problem is expressed as looking for extreme of a
function. Some function is given and GA tries to find minimum of the
function. For other problems we just have to define search space and the
fitness function which means to define the function, which we want to find
extreme for.
AI programming
15-puzzle (preliminary, only Depth-First-Search)
puzzle.c (complete) puzzle2.c
AI list library in C
Top-down parser package
Recursive programming with List
last update 4 Dec 2012