Title
Implementation of pulse-coupled neural networks in a CNAPS environment
Abstract
Pulse coupled neural networks (PCNN) are biologically inspired algorithms very well suited for image/signal preprocessing. While several analog implementations are proposed we suggest a digital implementation in an existing environment, the connected network of adapted processors system (CNAPS). The reason for this is two fold. First, CNAPS is a commercially available chip which has been used for several neural-network implementations. Second, the PCNN is, in almost all applications, a very efficient component of a system requiring subsequent and additional processing. This may include gating, Fourier transforms, neural classifiers, data mining, etc, with or without feedback to the PCNN
Year
DOI
Venue
1999
10.1109/72.761715
IEEE Transactions on Neural Networks
Keywords
Field
DocType
signal processing,intelligent networks,parallel computer,neural networks,backpropagation,signal generators,concurrent computing,circuits,image processing,fourier transforms,indexing terms,physics,back propagation,neurofeedback,neural network,data mining,feedback,gating
Signal processing,Computer science,Image processing,Fourier transform,Implementation,Chip,Multiprocessing,Preprocessor,Artificial intelligence,Artificial neural network,Machine learning
Journal
Volume
Issue
ISSN
10
3
1045-9227
Citations 
PageRank 
References 
7
1.31
8
Authors
2
Name
Order
Citations
PageRank
Jason M. Kinser1607.71
Thomas Lindblad271.31