Self-structuring hidden control neural models

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

The majority of neural models for pattern recognition have fixed architecture during training. A typical consequence is non-optimal and often too large networks. In this paper we propose a Self-structuring Hidden Control (SHC) neural model for pattern recognition, which establishes a near optimal architecture during training. We typically achieve a significant network architecture reduction in terms of the number of hidden Processing Elements (PE). The SHC model combines self-structuring architecture generation with non-linear prediction and hidden Markov modelling. The paper presents a theorem for self-structuring neural models stating that these models are universal approximators and thus relevant for real-world pattern recognition. Using SHC models containing as few as five hidden PES each for an isolated word recognition task resulted in a recognition rate of 98.4%. SHC models can furthermore be applied to continuous speech recognition.
Original languageEnglish
Title of host publicationNeural Networks for Signal Processing II : Proceedings of the 1992 IEEE-SP Workshop
PublisherIEEE Press
Publication date1992
Pages149-156
ISBN (Print)0-7803-0557-4
DOIs
Publication statusPublished - 1992
Externally publishedYes
Event1992 IEEE Workshop on Neural Networks for Signal Processing - Hotel Marielyst, Helsingoer, Denmark
Duration: 31 Aug 19922 Sep 1992
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=631

Workshop

Workshop1992 IEEE Workshop on Neural Networks for Signal Processing
LocationHotel Marielyst
CountryDenmark
CityHelsingoer
Period31/08/199202/09/1992
Internet address

Fingerprint

Dive into the research topics of 'Self-structuring hidden control neural models'. Together they form a unique fingerprint.

Cite this