Neural networks with dynamic structure using a GA-based learning method

Everett Fall, Hsin Han Chiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Artificial neural networks (NNs) are traditionally designed with distinctly defined layers (input layer, hidden layers, output layer) and accordingly network design techniques and training algorithms are based on this concept of strictly defined layers. In this paper, a new approach to designing neural networks is presented. The structure of the proposed NN is not strictly defined (each neuron may receive input from any other neuron). Instead, the initial network structure can be randomly generated, and traditional methods of training, such as back-propagation, are replaced or augmented by a genetic algorithm (GA). The weighting of each neuron input is encoded genetically to serve as the genes for the GA. By means of the training data provided to the supervised network, the contribution of each neuron in creating a desired output serves as a selection function. Each of the neurons is then modified to store and recall past weightings for possible future use. A simple network is trained to recognize vertical and horizontal lines as a proof of concept.

Original languageEnglish
Title of host publicationICNSC 2015 - 2015 IEEE 12th International Conference on Networking, Sensing and Control
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7-12
Number of pages6
ISBN (Electronic)9781479980697
DOIs
Publication statusPublished - 2015 Jun 1
Externally publishedYes
Event2015 12th IEEE International Conference on Networking, Sensing and Control, ICNSC 2015 - Taipei, Taiwan
Duration: 2015 Apr 92015 Apr 11

Publication series

NameICNSC 2015 - 2015 IEEE 12th International Conference on Networking, Sensing and Control

Other

Other2015 12th IEEE International Conference on Networking, Sensing and Control, ICNSC 2015
Country/TerritoryTaiwan
CityTaipei
Period2015/04/092015/04/11

Keywords

  • biologically inspired
  • complex neuron
  • deep learning
  • genetic algorithm
  • Neural network
  • weight retention

ASJC Scopus subject areas

  • Instrumentation
  • Control and Systems Engineering
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Neural networks with dynamic structure using a GA-based learning method'. Together they form a unique fingerprint.

Cite this