ECE 657 - Computational Intelligence / Intelligent Systems Design
Instructor
Fakhri Karray, extension (35584); Office E5-5029; e-mail: karray@uwaterloo.ca
Throughout the course there will be one or two invited lectures provided by guest professors/researchers. Flexible office hours throughout the week will be made available by appointment.
Course Outline
Conventional approaches for modeling and tackling complex systems are usually applied under the assumption of a good understanding of the system’s behavior/functionalities and its operating environment. These techniques fail, however, to provide satisfactory results when applied to ill-defined systems, for which analytical and experimental models may not be easily obtained. These same systems may also operate within unpredictable and possibly noisy/uncertain environments. Recent developments in the area of intelligent systems and machine learning have presented powerful alternatives for dealing with this class of systems. The course outlines fundamentals of soft computing based design approaches using such tools as approximate reasoning, machine learning, connectionist modeling, classification and clustering and evolutionary algorithms. Fundamentals and advances on these procedures are outlined along with their potential applications in various real world applications in virtually all fields of engineering including big data analytics, information retrieval, smart grid control, driverless cars, intelligent transportation, intelligent mechatronics, optimization, communication, robotics and manufacturing, to name a few.
Course Pre-requisite
ECE 650 is a pre-requisite for the course. Exceptions will be made through professor approval.
Lecture Time
Mondays and Fridays from 11:30 am - 12:50 pm in room E5 5106
TA for the Course
The TA for the course will be Mr. Alaa ElKhatib. His email address is:alaa.elkhatib@uwaterloo.ca. His office hours will be on Tuesdays and Thursdays from 10am until 11am.
Main Texts
Part of material taught in this course and assignments suggested are provided from the following literature:
- F. Karray and C. de Silva, Soft Computing and Intelligent Systems Design, Addison Wesley Publishing, Pearson Education, August 2004
- S. Marsland, Machine Learning, CRC Press, 2015
- Other online material tackling recent topics in the field of computational intelligence.
Other Possible Texts
- M. Negnevitsky, Artificial Intelligence, A Guide to Intelligent Systems, Pearson Publishing, 2006
- C. T. Lin and C.S. Lee, Neural Fuzzy Systems, Prentice Hall Publishing, 1995
- J. Jang, C. Sun, and E. Mizutani, NeuroFuzzy and Soft Computing, Prentice Hall Publishing, 1997
Course Scope
The course is useful for graduate students in virtually all areas of engineering, particularly for those dealing with complex systems at the soft or hard levels. A background in two or more of the following areas should be useful: fuzzy logic, artificial neural networks, machine learning, AI, system's optimization, nonlinear mapping, calculus of variation, differential calculus, statistical analysis, advanced algebra, game theory.
Course Material and Online Resources
All course material, including slides, notes, assignments, exams are posted on the course page on Learn. Exams and final projects are uploaded on the course web page on Learn.
Tentative Course Outline
The main sections of this course are given as follows:
- Introduction
- Approximate Reasoning, Fuzzy Inferencing and Intelligent Systems
- Introduction to Machine Learning and Fundamentals of Connectionist Modelling
- Major Classes of Artificial Neural Networks and Introduction to Deep Learning
- Classifiers, Nonlinear Regression and Support Vector Machines
- Evolutionary Techniques and Hybrid Systems
Course Requirement
-
Assignments
(0%):
Assignments will be provided on a biweekly to tri-weekly basis. Students are highly encouraged to solve them
-
Midterm
(25%):
A midterm will be assigned around last week of June
-
Journal
Paper
Analysis
and
Presentation
(20%)
The student is required as part of the course workload to analyze, and possibly synthesize results of one or more journals publication in one of the areas related to the course. The areas will be outlined around the third week of the course.
-
Final
Exam
(55%)
As the final exam requirements, the student is asked to work on a final project illustrating and making use of the some of the theory, topics and tools taught during the term.
Library Material
A large set of relevant of journals and texts related to the subject are available in the library or online, including:
- IEEE Transactions on Fuzzy Systems
- IEEE Transactions on Neural Networks and Learning Systems
- IEEE Transactions on Evolutionary Computation
- IEEE Transactions on Cybernetics
- Fuzzy Sets and Systems