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

Alfons Schuster, Daniel Berrar

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルBiomedical Informatics and Technology - 1st International Conference, ACBIT 2013, Revised Selected Papers
出版社Springer Verlag
ページ219-234
ページ数16
ISBN(印刷版)9783642541209
DOI
出版ステータスPublished - 2014 1 1
イベント1st International Aizu Conference on Biomedical Informatics and Technology, ACBIT 2013 - Aizu-Wakamatsu, Japan
継続期間: 2013 9 162013 9 17

出版物シリーズ

名前Communications in Computer and Information Science
404 CCIS
ISSN(印刷版)1865-0929

Conference

Conference1st International Aizu Conference on Biomedical Informatics and Technology, ACBIT 2013
国/地域Japan
CityAizu-Wakamatsu
Period13/9/1613/9/17

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)
  • 数学 (全般)

フィンガープリント

「Towards Nature-Inspired Modularization of Artificial Neural Networks via Static and Dynamic Weights」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル