CMPS 460 - Design & Implementation of Neural Networks

Spring 2007

Instructor:                         Dr. Cris Koutsougeras

Office:                               307C      Fayard Hall
Telephone:                        (985) 549-3479
Email:                               ck @t
Web Page:              
Office Hours:                     T, R     2:00PM - 3:30PM

Textbook:    “Digital Neural Networks”, S.Y. Kung, Pearson Prentice Hall, ISBN: 0-13-612326-0. Also you may consider the more comprehensive (but more difficult to follow) book “Neural Networks” (2nd Edition), by Simon Haykin, Publisher: Prentice Hall, ISBN: 0-13-273350-1. Another alternative is the (not quite comprehensive but much easier to follow) “An Introduction to Neural Networks” by K. Gurney, Publisher: CRC, ISBN-13: 978-1857285031

Course Prerequisite:         Math360.

Course Description:          Introduction to the basic concepts of neural networks: what are neural networks, applications, learning from examples, adaptation, forecasting, curve fitting, pattern classification, associative memory. A set of the most popular and fundamental models will be presented: Backpropagation, Hopfield, Kohonen, clustering and entropy, pottential fields, recurrent nets, and more as time permits.

Minimum Course Topic coverage:          This course covers at least the following topics:

  • Perceptrons
  • Non-linear regression, Backpropagation
  • Simulated annealing
  • Pattern classification/clustering: Entropy, Support Vector Machines
  • Radial Basis Function Networks
  • Self Organizing Maps
  • Counterpropagation
  • Potential Fields methods
  • Hopfield Nets, Associative memories, Optimization
  • Recurrent Nets

Course Objectives:  Students will be able to:

  • Become familiar with a few different fundamental neural net models which cover a range of different functionalities.
  • Analyze and understand the function and behavior of the basic and fundamental neural net models covered in this course.
  • Design, implement, and test an application that uses a neural net simulator.
  • Become familiar with advanced AI principles and methods (such as pattern classification, learning from examples, optimization, statistical learning methods, data mining).
  • Recognize the difference between the symbolic and sub-symbolic computer paradigms.
  • Become familiar with the benefits of the neural networks approach and their suitability for various engineering applications.

Course Outcomes: 

  • An ability to apply knowledge of mathematics and science to the analysis of engineering problems.
  • An ability to conduct scientific and engineering experiments, and interpret data.
  • An ability to design a system, component, or process to meet desired needs.
  • An ability to function on multidisciplinary problems.
  • An ability to identify, to formulate, and to solve engineering and other problems.
  • An ability to convey technical material through formal written work that satisfy accepted standards for writing style.
  • An ability to convey technical material through oral presentation and interaction with an audience.
  • A recognition of the need for, and the ability to engage in life-long learning.
  • A knowledge of probability and statistics, including computer and engineering applications.
  • An ability to use modern engineering techniques, skills, and tools, including computer-based tools for analysis and design.
  • An ability to perform area-specialized independent research.
  • An ability to critique and motivate the research projects performed by others.
  • An ability to engage and solve open ended problems.

Grading Policy:  Grades to be determined by curve method on total score which will be computed as follows:

  • Class Quizzes                                 5%
  • Projects                                        25%
  • Tests  (2 midterms)                        20% (each)
  • Final Examination                          30%

Attendance:  Attendance is mandatory for all sessions of this course. Students who have more than 6 non-excused hours will be dropped from the course. Absences can be excused only with proper and verifiable supportive documentation, such as a physician’s note.

Quizzes: There will be a number of quizzes during this term. There are no makeups for missed quizzes.

Projects:  Homeworks will be collected periodically. Selected problems will be graded. No late homeworkswill be accepted unless special permission has been explicitly granted.

Examinations:  There will be two midterms and a final examination. At the instructor’s discretion, makeups for missed examinations may be given and only with proper documentation of an emergency that can reasonably justify the absence. If a makeup is not agreed after you miss an examination with an excusable absence, your grade for this missed examination will be the score of your final examination. If your absence is not excused, you will receive a grade of zero on the examination you missed.

ADA Accommodation:  If you are a qualified student with a disability seeking accommodations under the Americans with Disabilities Act, you are required to self-identify with the Office of Disability Services, Room 203, Student Union. More information can be obtain at this web address,

Classroom Decorum:  Free discussion, inquiry, and expression are encouraged in this class. Classroom behavior that interferes with either (a) the instructor’s ability to conduct the class or (b) the ability of students to benefit from the instructor is not acceptable. Examples include routinely entering class late or departing early; use of beepers, cellular telephones, or other electronic devices; repeatedly talking in class without being recognized; talking while others are speaking; or arguing in a way that is perceived as “crossing the civility line.” In the event of a situation where a student legitimately needs to carry a beeper or cellular telephone to class, prior notice and approval of the instructor is required.

The office/classroom is not a place for children and neither employees or students are to bring their family members for day care or baby sitting. If children require care, then the employee/student is expected to provide that care in an environment other than Southeastern office/classroom space.

Other information:   

  • No one can be permitted to continue attending class unless listed on the class roster (available after the 14th day of classes).
  • Thursday, February 15 is the last day to withdraw  or resign from Term I classes.
  • Friday, March 16 is the last day to withdraw or resign from regular classes.
  • Thursday, April 19 is the last day to withdraw  or resign from Term II classes.
  • Monday, May 14 is the last day to return rental textbooks without a fine.

Academic integrity:

“Students are expected to maintain the highest standards of academic integrity. Behavior that violates these standards is not acceptable. Examples are the use of unauthorized material, communication with fellow students during an examination, attempting to benefit from the work of another student and similar behavior that defeats the intent of an examination or other class work. Cheating on examinations, plagiarism, improper acknowledgment of sources in essays and the use of a single essay or paper in more than one course without permission are considered very serious offenses and shall be grounds for disciplinary action as outlined in the current General Catalogue.”

Plagiarism through use of Turnitin:

Students agree by taking this course that all required papers may be subject to submission for textual similarity to for the detection of plagiarism. All submitted papers will be included as source documents in the reference database solely for the purpose of detecting plagiarism of such papers. Use of the service is subject to the Terms and Conditions of Use posted on the website.”