The EE-method, an evolutionary engineering developer tool: neural net case study

Summary form only given. Evolutionary engineering (EE) challenge is to prove that it is possible to build systems (i.e. solutions) without going through any design process. Evolutionary engineering is defined to be "the art of using evolutionary algorithms approach such as genetic algorithms to...

Full description

Saved in:
Bibliographic Details
Main Authors: Lehireche, A., Rahmoun, A.
Format: Conference Proceeding
Language:English
Subjects:
Computer aided software engineering
Computer science
Design engineering
Evolutionary computation
Genetic algorithms
Genetic engineering
Genetic programming
Neural networks
Process design
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Summary form only given. Evolutionary engineering (EE) challenge is to prove that it is possible to build systems (i.e. solutions) without going through any design process. Evolutionary engineering is defined to be "the art of using evolutionary algorithms approach such as genetic algorithms to build complex systems". Our main goal is to show that the EE-method is a good setting. We show step by step, using the EE-method, how to build a neural net based system. The EE-method can be viewed as just a GP appliance. The need of a well-specified approach determines the necessity for such a method. To bring the EE-method into operation, we had implemented software to build/evolve neural net-based systems. As an example, we present an evolved neural net Xor.
DOI:10.1109/AICCSA.2003.1227552