SINAI UNIVERSITY
FACULTY OF INFORMATION TECHNOLOGY
CSW (351) Artificial Intelligence – Syllabus, Fall 2010
Professor Dr. Hamed Sallam
Note: Dr. Sallam Will come to class the first week of October.
However students should attend the lectures on time and report to
the TA, and submit their home works to Professor Sallam’s email on
time. Thanks
E-mail: (hamed.sallam@mnsu.edu)
Teacher Assistant: Mr. Mohamed Loey E-mail:
mohamedloey@gmail.com
Pre-requisite: Computer programming1
Course Description: The goal of Artificial Intelligence is to build
software systems that behave "intelligently". By this, we mean that the
computer systems "do the right thing" in complex environments--that
they act optimally given the limited information and computational
resources available. This course provides an introduction to artificial
intelligence. We will first study the core topics of knowledge
representation, reasoning, and learning, all from the perspective of
probabilistic methods. Then we will cover several of the "subject areas"
of artificial intelligence where these probabilistic methods are applied
including Natural Language Processing, Perception (primarily vision),
and Robotics. Introduction to Fuzzy-Neuro Systems will be also
introduced with their industrial applications
Learning Objectives
By the end of the course, you should be able to do the following:
o Represent the causal structure of a given domain using
Bayesian networks and use it to make both quantitative
(probabilistic) and qualitative inferences.
o Given a simple version of a problem such as object
recognition or text categorization, implement a bayesian
network that solves the problem and explain how learning
takes place in the bayesian network.
1
Identify the steps in natural language processing, list some of
the problems in understanding and generation, and describe
how information retrieval, information extraction, and
language translation systems work.
o Choose an appropriate method for robot navigation and
justify its choice over other methods such as exhaustive
search and exact inference.
o Recognize when a problem is not amenable to a traditional
programming (e.g., procedural, object-oriented, etc) solution,
but might be amenable to knowledge-based or learning-based
methods.
o Introducing the state-of-the art in Fuzzy-Neuro- technology
Teaching Material:
 Text- Artificial Intelligence: A Modern Approach (third edition) by
Stuart Russell and Peter Norvig (recommended).
 Lecture notes by Sallam - Available on the course website: Coming
Soon
Grading scheme:
 Make-ups for homework or tests may be granted for valid excuses.
 Assignments/Homework/Quizzes: 15%
 Mid Term: 15%
 Projects :20%
 Final : 50%
Grading scale :( 100 Max) Grading scale :( 100 Max)
- A (90 -100) - A- (85 – 90) - B+ (80 – 85) - B (75 – 80)
- B- (72.5 – 75) C+ (70 - 72.5) - C (67.5 – 70) - C- (65 - 67.5)
- D+ (62.5 – 65) - D (60 -62.5) - F < 60
Late submissions: Late submissions of homework will be penalized with
a deduction of 10% of the grade per late day, to a maximum of two late
days for each submission.
Tentative schedule (TBA)
o
2