Characterization of Analog Local Cluster Neural Network Hardware for Control

Sitte, J., Zhang, L. and Rueckert, U (2007) Characterization of Analog Local Cluster Neural Network Hardware for Control. IEEE Transactions on Neural Networks, 18 4: 1242-1253.

Document type: Journal Article
Collection: Security and Surveillance Collection

Author(s) Sitte, J.
Zhang, L.
Rueckert, U
Title Characterization of Analog Local Cluster Neural Network Hardware for Control
Journal name IEEE Transactions on Neural Networks
Publication date 2007
Sub-type Article
Volume number 18
Issue number 4
ISSN 1045-9227
Start page 1242
End page 1253
Total pages 12
Publisher IEEE
Language eng
Subject 290902 Integrated Circuits
280212 Neural Networks, Genetic Alogrithms and Fuzzy Logic
Abstract The local cluster neural network (LCNN) was designed for analog realization especially suited to applications in control systems. It uses clusters of sigmoidal neurons to generate basis functions that are localized in multidimensional input space. Sigmoidal neurons are well suited to analog electronic realization. In this paper, we report the results of extensive measurements that characterize the computational capabilities of the first analog very large scale integration (VLSI) realization of the LCNN. Despite manufacturing fluctuations and the inherent low precision of analog electronics, the test results suggest that it may be suitable for use in feedback control systems.
Keyword(s) analog computation
analog very large scale integration
function approximation
neural networks
radial basis function (RBF) networks
 
Related Links
Link Description
http://dx.doi.org/10.1109/TNN.2007.899518  
Go to link with your UQ access privileges  		 Link to Full text via DOI  
 
Versions
Version Filter Type
Access Statistics: 27 Abstract Views  -  Detailed Statistics
Created: Wed, 25 Jun 2008, 14:34:21 EST by Anne Draper on behalf of Social Sciences and Humanities Library Service  -  Detailed History