Artificial Intelligence (AI) can be defined as the branch of computer science that is concerned with the automation of intelligent behavior.

Goals for the course

• Understand that there are a variety of representations used to encode knowledge in AI problems. These representations can be classified along a continuum from symbolic to subsymbolic. Symbolic representations are atomic and discrete, such as in formal logic. Subsymbolic representations are distributed and continuous, such as a vector of numerically encoded features.
• Understand that there are a variety of paradigms for approaching AI problems including search, machine learning, embodiment, and emergence.
• Be able to compare and contrast the strengths and weaknesses of each approach.
• Given a particular AI problem, be able to determine an appropriate representation and approach for solving it.
• Be able to respond to the common objections to the possibility of achieving AI, such as Lady Lovelace's objection that a computer can only do what we tell it to do and therefore cannot create anything new.

Class information

Room: Science Center 246
Time: Tuesday, Thursday 2:40pm–3:55pm

Professor: Lisa Meeden
Office: Science Center 243
Phone: 328-8565
Office hours:Wednesday 2-4pm or by appointment

Readings: We will be reading a selection of chapters from AI textbooks as well as articles from the primary literature. Some of these materials are available online, and can be found as links in the schedule below. The remaining materials are available in binders and can be picked up at the CS department office. Complete reading list

Schedule

WEEK	DAY	ANNOUNCEMENTS	TOPIC & READING	HOMEWORK
1	Sep 04		Foundations of AI McCarthy, Minsky, Rochester and Shannon article Turing article Success of AI 2005 DARPA grand challenge	Learn python Python tutorial Online Python book
	Sep 06
	Sep 11	Quiz 1	Search Russell and Norvig, Ch. 3	1: State space search
	Sep 13	Drop/Add ends (Sep 14)
	Sep 18		Informed search Russell and Norvig, Ch. 4	2: A* search
	Sep 20
	Sep 25	Quiz 2	Evolutionary search Mitchell, Ch. 1 Breeding Better Buildings	3: Genetic algorithm
	Sep 27
	Oct 02		Adversarial search: Game playing Russell and Norvig, Ch. 6 Schaeffer article	4: Minimax search
	Oct 04
	Oct 09	Quiz 3	Success of AI Deep Blue	Game tournament
	Oct 11
	Oct 16	Fall Break
	Oct 18
	Oct 23		Neural networks Munakata, Ch. 2	5: Back propagation
	Oct 25
	Oct 30	Quiz 4	Advanced networks Schultz, Ch. 2 Elman article	None
	Nov 01
	Nov 06		Reinforcement learning Tesauro article	6: Learning to play TicTacToe
	Nov 08	Last day to declare CR/NC or withdraw with a W (Nov 09)
	Nov 13	Quiz 5	Embodied approach Pfiefer and Scheier, Ch. 3 Harnad article	None
	Nov 15
	Nov 20		Emergence Braitenberg, Chs. 1-6	7: Simulated vehicles
	Nov 22	Thanksgiving Break
	Nov 27	Quiz 6	Behavior-based robots Brooks article	8: Subsumption Challenge results
	Nov 29
	Dec 04		Learning robots Nolfi article Meeden article	None
	Dec 06
	Dec 11		Review
	Dec 20	Final 2-5pm

Grading

Your overall grade in the course will be determined as follows:

30%	Quizzes
45%	Homework
5%	Class Participation
20%	Final Exam

Homework policy

All programming assignments will be done in Python.

Programming assignments will typically be assigned in class at the end of the week and will be due before noon the following Friday. You are strongly encouraged to start early.

You will submit your assignments electronically using the handin63 program. You may submit your assignment multiple times, but each submission overwrites the previous one and only the final submission will be graded. Late assignments will not be accepted unless you contact me before the deadline. Even if you do not fully complete an assignment, you may submit what you have done to receive partial credit.

External Links

Python Documentation