A fast modified constructive-covering algorithm for binary multi-layer neural networks

For binary neural networks (BNNs), constructive covering frameworks have been investigated recently. While these frameworks are fast, they have limitations of generalization and accurate classification for learning from limited number of samples. In this paper, we propose modified constructive-cover...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) Jg. 70; H. 1; S. 445 - 461
Hauptverfasser: Wang, Di, Chaudhari, Narendra. S.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.12.2006
Schlagworte:
Binary neural networks
Constructive learning
Geometrical learning
Linearly separablility
Multi-layer neural networks
Geometrical learning
Binary neural networks
Constructive learning
Multi-layer neural networks
Linearly separablility
ISSN:0925-2312, 1872-8286
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:For binary neural networks (BNNs), constructive covering frameworks have been investigated recently. While these frameworks are fast, they have limitations of generalization and accurate classification for learning from limited number of samples. In this paper, we propose modified constructive-covering algorithm (MCCA), which consists of two processes: generalization process and modification process. Errors introduced in the generalization process are revised in the modification process by adding modification neurons. In our approach, we visualize hidden neurons in terms of hypershperes. The learning process is the geometrical expansion process of these hypershperes. Through our experimental work in Section 5, we conclude that, MCCA is not sensitive to the order in which the input sequence is given. In addition, MCCA results in simple neural network structures by less training time.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2005.12.124