Incremental neural learning by dynamic and spatial changing weights

Noriyasu Homma, Madan M. Gupta

研究成果: Conference contribution

抄録

In this paper a new neural network model is presented for incremental learning tasks where networks are required to learn new knowledge without forgetting the old one. An essential core of the proposed neural network structure is their dynamic and spatial changing connection weights (DSCWs). A learning scheme is developed for the formulation of the dynamic changing weights, while a structural adaptation is formulated by the spatial changing (growing) connecting weights. To avoid disturbing the past knowledge by the creation of new connections, a restoration mechanism is introduced by using the DSCWs. Usefulness of the proposed model is demonstrated by using a system identification task.

本文言語English
ホスト出版物のタイトルIFAC Proceedings Volumes (IFAC-PapersOnline)
編集者Gabriel Ferrate, Eduardo F. Camacho, Luis Basanez, Juan. A. de la Puente
出版社IFAC Secretariat
ページ247-252
ページ数6
1
ISBN(印刷版)9783902661746
DOI
出版ステータスPublished - 2002
イベント15th World Congress of the International Federation of Automatic Control, 2002 - Barcelona, Spain
継続期間: 2002 7月 212002 7月 26

出版物シリーズ

名前IFAC Proceedings Volumes (IFAC-PapersOnline)
番号1
15
ISSN(印刷版)1474-6670

Other

Other15th World Congress of the International Federation of Automatic Control, 2002
国/地域Spain
CityBarcelona
Period02/7/2102/7/26

ASJC Scopus subject areas

  • 制御およびシステム工学

フィンガープリント

「Incremental neural learning by dynamic and spatial changing 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