COURSE TITLE (COURSE CODE)

The Higher Canadian Institute for Business
and Engineering Technology
Quality Assurance Unit
Course Specification
Course Name: Neural Networks
Course Code: COMP 424
I. Basic Course Information
Program(s) on which the course is given: Computer Engineering
Core or elective element of program Elective
Department offering the course: Engineering Department
Academic level:4
Semester in which course is offered: Spring
Course pre-requisite(s): Advanced Programming C++ COMP 412
Credit Hours: 3
Contact Hours Through:4
Lecture
2.0
Tutorial*
2.0
Practical*
0.0
Total
4.0
Approval date of course specification: September 2013
II. Overall Aims of Course
- Upon completion of this course, students will be able to:
-Understand the importance of artificial neural networks
-Have detailed knowledge of neural network design principles
-Know the basic approaches to growing and pruning neural networks
-Undertake analysis of neural network performance
-Understand the importance of over fitting avoidance in neural network learning
-Understand the differences between the various network architectures
-Have abilities for practical application of neural networks
III. Program ILOs covered by course
Program Intended Learning Outcomes (By Code)
Knowledge &
Intellectual Skills
Professional Skills
Understanding
K1, K4, K5, K12
I2, I5 ,I6, I9
P1, P4, P6
General
Skills
G2, G3, G4
1
The Higher Canadian Institute for Business
and Engineering Technology
Quality Assurance Unit
Course Specification
IV. Intended Learning Outcomes of Course (ILOs)
a. Knowledge and Understanding
On completing the course, students should be able to:
k1. Identify and demonstrate competence in university level mathematics, natural sciences,
engineering fundamentals, and specialized engineering knowledge appropriate to the program.
k2. Relate practical application of theories in different fields through projects and field
studies.
k3. Express unique oriented Knowledge in the relevant fields.
k4. Recognize principles and methods of design used in computer engineering.
b. Intellectual/Cognitive Skills
On completing the course, students should be able to:
i1. Use brain storming and innovation techniques to deal with problems and to develop new
ideas.
i2. Use and develop computer programs.
i3. Apply solutions for complex, open-ended engineering problems.
i4. Apply appropriate computer based methods for modelling and analyzing problems in
electrical and electronic engineering.
c. Practical/Professional Skills
On completing the course, students should be able to:
p1. Formulate and use the appropriate mathematical methods for modelling and analyzing
problems in electrical, electronic and communications engineering.
p2. Collect information and develop new ideas
p3. Design, build and test a communication system.
d. General and Transferable Skills
On completing the course, students should be able to:
g1. Use the scientific evidence based methods in the solution of problems.
g2. Use of general IT tools.
g3. Express creativity and innovation in problem solving and working with limited or
contradictory information.
V. Course Matrix Contents
Main Topics / Chapters
12345-
Basic neural network
architectures
Learning algorithms
Neuron Model and Network
Architectures
Learning rules
Background on performance
surfaces and optimization.
Widrow-Hoff Learning
Duration
(Weeks)
Course ILOs Covered by Topic
(By ILO Code)
K&U
I.S.
P.S.
G.S.
2
k1
i1
2
k2
i1, i2
p1
2
k1, k3
i3
p2
4
k2
i4
1
k4
i2, i3, i4
g1
2
The Higher Canadian Institute for Business
and Engineering Technology
Quality Assurance Unit
Course Specification
6- Back propagation
7- Boltzmann machine
Net Teaching Weeks
1
1
13
k4
k4
i4
i4
g2
g3
p3
VI. Course Weekly Detailed Topics / hours / ILOs
Week
No.
1
2
3
4
5
6
Sub-Topics
Introduction to Neural networks
Basic neural network architectures
Learning algorithms
Learning algorithms
Neuron Model and Network
Architectures
Neuron Model and Network
Architectures
7
8
9
10
11
12
13
14
15
Contact Hours
Theoretical
Practical
Hours
Hours*
2
2
2
2
2
2
2
Total
Hours
2
4
4
4
4
2
2
4
2
2
2
2
2
2
2
2
2
2
2
2
2
2
2
2
Midterm Exam
Competitive Networks. Perceptron
4
Learning Rule
Competitive Networks. Perceptron
4
Learning Rule
Supervised Hebbian Learning
4
Supervised Hebbian Learning
4
Background on performance surfaces and
4
optimization. Widrow-Hoff Learning
Back propagation
4
Boltzmann machine
4
Final Exam
Total Teaching Hours
VII. Teaching and Learning Methods
Teaching/Learning
Method
Lectures & Seminars
Tutorials
Computer lab Sessions
Practical lab Work
Reading Materials
Web-site Searches
Research & Reporting
Problem Solving /
Problem-based Learning
Projects
Independent Work
Course ILOs Covered by Method (By ILO Code)
K&U
All
All
Intellectual
Skills
All
All
All
Professional
Skills
All
General
Skills
All
All
All
All
3
The Higher Canadian Institute for Business
and Engineering Technology
Quality Assurance Unit
Course Specification
Group Work
Case Studies
Presentations
Simulation Analysis
Others (Specify):
VIII. Assessment Methods, Schedule and Grade Distribution
Course ILOs Covered by Method
(By ILO Code)
Assessment
Method
K&U
I.S.
P.S.
G.S.
Midterm Exam
All
Final Exam
All
Quizzes
All
Course Work
Report Writing
Case Study
Analysis
Oral
Presentations
Practical
Group Project
Individual Project
All
All
All
All
Assessment
Weight /
Percentage
All
All
All
20 %
[50 %]
10 %
10 %
All
All
10 %
Week
No.
Others (Specify):
IX. List of References
Essential Text Books
Course notes
Recommended books
Periodicals, Web sites,
etc …
- Haykin, Simon. Neural Networks. A Comprehensive Foundation.,
Second Edition, Prentice-Hall, Inc., New Jersey, 1999
Course Management System CMS
X. Facilities required for teaching and learning
big sized lecture rooms - computers (Personal & Notebook) - data show
Course coordinator: Associate Professor. Alaa Hamdy
Head of Department: Associate Professor/ Tamer Abdel Rahman
Date: September 2013
4