Neural Networks
Catalog Data: 

Graduate Course Information


ECE 631 - Neural Networks

Credits: 3.00

Course Website: D2L

UA Catalog Description:

Course Assessment:

Homework:  8 – 10 assignments

Project:  1 project

Exams:  2 Midterm Exams, 1 Final Exam

Grading Policy:

Typically: 40% Midterms,

                  40% Final Exam,

                  20% Project.

Course Summary: Neural networks represent a novel form of computing that is motivated by the highly parallel processing that takes place in biological systems. The course will present the theory and application of parallel distributed computation via elementary processing elements; neuron models and biological analogies; relationships between neural networks and statistical classification, supervised/unsupervised learning; neural net models; associative memories; training algorithms

Graduate Standing

Required: Simon Haykin, “Neural Networks: A Comprehensive Foundation,” 2nd Edition, Prentice Hall, 1999. Although this text will be required for the course, significant supplementary materials will be presented as class notes. The following list of references may also prove helpful for occasionally consultation.

Duda and Hart, “Pattern Analysis and Scene Classification,” John Wiley & Sons, 1973.

Bishop, “Neural Networks for Pattern Recognition,” Oxford University Press, 1995.

Cherkassky and Mulier, “Learning From Data,” John Wiley & Sons, 1998.

Course Topics: 

1.     Introduction to Neurocomputing (CH1)

2.     Learning and Generalization (CH2)

3.     The Neuron (CH3)

4.     Multi-Layer Networks (CH4)

5.     Miscellaneous Network Studies

a.     - Regularization Nets (CH5)

b.    - Competitive Nets (CH9)

c.     - Support Vector Machines (CH6)

6. Feedback and Optimization Nets (CH14)

Class/Laboratory Schedule: 

Lecture:  150 minutes/week

Prepared by: 
Mark Neifeld
Prepared Date: 
April 2013

University of Arizona College of Engineering