Title: Introduction to Artificial Intelligence
|Times & Days||Office Hours|
What is AI -- AI In the News -- References -- Grading Scheme -- Lectures and Assignments -- Related Courses
Virtual class attendance
of the course for European exchange students: July 17 - Aug 4, 2006
The objective of the course is to familiarize the student with fundamental concepts of artificial intelligence, with equal emphasis on numeric(statistical) and symbolic techniques. Another objective is to prepare the student both for further study in artificial intelligence and for practical work in the applications of artificial intelligence to areas such as data mining, web information systems, bioinformatics, biometrics, robotics.
Calendar entry (incl. prerequisites)
What is Artificial
Intelligence (ask the experts)
|Ever since computers were invented, it has been natural to
wonder whether they might be able to learn. Imagine computers learning
from medical records to discover emerging trends in the spread and treatment
of new diseases, houses learning from experience to optimize energy costs
based on the particular usage patterns of their occupants, or personal software
assistants learning the evolving interests of their users to highlight especially
relevant stories from the online morning newspaper.
- Tom M. Mitchell, AAAI President (2001 - 2003)
|. . . Exactly what the computer provides is the ability not to be rigid
and unthinking but, rather, to behave conditionally. That is what
it means to apply knowledge to action: It means to let the action taken
reflect knowledge of the situation, to be sometimes this way, sometimes
that, as appropriate. . . . In sum, technology can be controlled especially
if it is saturated with intelligence to watch over how it goes, to keep
accounts, to prevent errors, and to provide wisdom to each decision.
-Allen Newell, from Fairy Tales
AI in the News
Stuart Russell and Peter Norvig: Artificial
Intelligence: A Modern Approach
Publisher: Prentice Hall; 2nd edition (December 20, 2002) ISBN: 0137903952
David J. C. MacKay: Information
Theory, Inference and Learning Algorithms
Cambridge University Press, 2003, ISBN: 0521642981 (pdf file available for on-screen reading only)
Nils J. Nilsson: "Artificial Intelligence : A New Synthesis", Morgan Kaufman Publishers (April 1998); ISBN: 1558604677
M. Watson: "Intelligent Java Applications for the Internet and Intranets", Morgan Kaufmann, 1997.
Sutton and Barto: "Reinforcement Learning", MIT Press. (draft is available online)
D Poole, A Mackworth and R Goebel, Computational Intelligence: A Logical Approach , Oxford, 1998.
American Association for Artificial Intelligence: Links
to Resources -- AI
Russ Greiner's AI course at the Univ. of Alberta (with many useful pointers)
B-Course: A Bayesian Data Analysis tutorial (Univ. of Helsinki)
CI-space: Tools for Learning Computational Intelligence (UBC)
Mahdi Shafiei's AI course for the EU-Canada exchange program (Dal, summer 2006)
35% assignments (4 equally weighted assignments)
30% student project (in groups)
An important part of the course is the project. Students will work in groups of two on a programming project related to any of the topics covered in the course. Please review project guidelines. Options 1 and 2 are the most suitable for this class.
The exam is closed-book. To minimize the need for memorization, a two-page crib sheet is permitted (no magnifying devices). Compiling a useful crib sheet is a good way to guide your review of the course material for the exam.
Late assignments are only acceptable when accompanied by a doctor's note stating the period of illness. Deferred deadline must be requested on the first day after the end of illness.
Please familiarize yourself with the Faculty's Plagiarism Policy. Every suspected case of plagiarism will be referred to the Senate Discipline committee, and the standard penalty for a first offence is failure in the course.
Students with disabilities are encouraged to register as quickly as possible at the Student Accessibility Services if they want to receive academic accommodations. To do so please phone 494-2836, e-mail access <at-symbol> dal.ca , drop in at the Killam, G28 or visit our website at www.studentaccessibility.dal.ca .
Related Courses at Dalhousie U.
CSCI 2140 Data & Knowledge Fundamentals. Core course which covers search and logic. It is a core course in the curriculum, and all students are assumed to have taken it.
CSCI 4144 & CSCI 6405: Data Mining and Data Warehousing. Focus on link to databases, pre/post processing of data.
MATH 5500. Statistical Data Mining: Statistical treatment of supervised and unsupervised learning.
CSCI 6501. Intelligent Systems.
CSCI 6504. Software Agents: Reinforcement learning, grammar induction
CSCI 6506 Genetic Algorithms and Programming. In-depth treatment of this topic
CSCI 6507. Artificial Neural Networks.
CSCI 6508. Computational Neuroscience.
CSCI 6509. Advanced Topics in Natural Language Processing. Uses machine learning techniques (Hidden Markov Models, Naive Bayes, Clustering).