Implementation of pulse-coupled neural networks in a CNAPS environment

J M Kinser; T Lindblad

doi:10.1109/72.761715

Implementation of pulse-coupled neural networks in a CNAPS environment

IEEE Trans Neural Netw. 1999;10(3):584-90. doi: 10.1109/72.761715.

Authors

J M Kinser¹, T Lindblad

Affiliation

¹ Royal Institute of Technology, Department of Physics (Frescati), Stockholm S-104 05, Sweden.

PMID: 18252556
DOI: 10.1109/72.761715

Abstract

Pulse coupled neural networks (PCNN's) 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.