Friday 24th of November 2017
 

A Framework for an Automatic Generation of Neural Networks


Belal Al-Khateeb and Maha Mahmood

The automatic generation of neural network architecture is a useful concept as in many applications while the optimal architecture is not a priori known. Often trial and error is done before a satisfactory architecture is found. Construction deconstruction algorithms can be used as an approach but they have several drawbacks. Sometimes an evolutionary computation and evolutionary algorithms are used but the idea in this paper is reserved for a special kind of evolutionary algorithms. So in this paper we proposed framework for neural networks which try to get best solution for problems by automatic generation technique. The obtained results are promising, suggesting many other research directions.

Keywords: neural network, evolutionary algorithms, genetic programming, genetic algorithms.

Download Full-Text


ABOUT THE AUTHORS

Belal Al-Khateeb
Belal Al-Khateeb received the B.Sc. (honors) (first class) degree in computer science from Al-Nahrain Universi-ty, Baghdad, IRAQ, in 2000, and the M.Sc. degree in com-puter science from Al-Nahrain University, Baghdad, IRAQ, in 2003, and the Ph.D. degree from the School of Computer Science, University of Nottingham, Nottingham, U.K., in 2011. He is currently a lecturer at the College of Computer, Al-Anbar University. He has published over 15 refereed journal and conference papers. His current research interests include evolutionary and adaptivelearning particularly in computer games, expert systems, and heuristics and me-ta/hyper-heuristics. He has a particular interest in computer games programming. Dr. Al-Khateeb is a reviewer of two international journals (including one IEEE Transaction) and four conferences .

Maha Mahmood
Maha Mahmood received the B.Sc. (first class) degree in computer science from Al-Anbar Universi-ty, Ramadi, IRAQ.


IJCSI Published Papers Indexed By:

 

 

 

 
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »