Towards Nature-Inspired Modularization of Artificial Neural Networks via Static and Dynamic Weights

Alfons Josef Schuster, Daniel Berrar

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

Abstract

Many conventional artificial neural network (ANN) models are designed for one application domain only. The work presented in this paper describes ANN models that operate with a higher economy by sharing neurons across domains. The use of two different types of weights-static weights and dynamic weights-is a fundamental feature of the presented models. Results from a comprehensive series of experiments provide evidence for the meaningfulness of the proposed models.

Original languageEnglish
Title of host publicationCommunications in Computer and Information Science
PublisherSpringer Verlag
Pages219-234
Number of pages16
Volume404 CCIS
ISBN (Print)9783642541209
DOIs
Publication statusPublished - 2014
Event1st International Aizu Conference on Biomedical Informatics and Technology, ACBIT 2013 - Aizu-Wakamatsu
Duration: 2013 Sep 162013 Sep 17

Publication series

NameCommunications in Computer and Information Science
Volume404 CCIS
ISSN (Print)18650929

Other

Other1st International Aizu Conference on Biomedical Informatics and Technology, ACBIT 2013
CityAizu-Wakamatsu
Period13/9/1613/9/17

    Fingerprint

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Schuster, A. J., & Berrar, D. (2014). Towards Nature-Inspired Modularization of Artificial Neural Networks via Static and Dynamic Weights. In Communications in Computer and Information Science (Vol. 404 CCIS, pp. 219-234). (Communications in Computer and Information Science; Vol. 404 CCIS). Springer Verlag. https://doi.org/10.1007/978-3-642-54121-6_19