Documento de conferencia

Current-mode implementation of processing modules in ART-based neural networks

Conference Proceeding cp
Proceedings of SPIE - The International Society for Optical Engineering
  • Volumen: 5119
  • Fecha: 22 septiembre 2003
  • Páginas: 35-45
  • ISSN: 0277786X
  • Tipo de fuente: Ponencia
  • DOI: 10.1117/12.499188
  • Tipo de documento: Documento de conferencia
This paper describes the implementation of neural network processing layers using basic current-mode operating modules. The research work has been focused on the implementation of neural networks based on the Adaptive Resonance Theory, developed by S. Grossberg and G.A. Carpenter. The ART-based neural network whose operating modules have been chosen for development is the one called MART because of its complex architecture, auto-adaptive self-learning process and its ability to discard unmeaningful categories. The analog circuit described in the following lines matches the monochannel block included in the main signal processing part of the MART neural network.

Palabras clave del autor

    Palabras clave indexadas

      Detalles de financiación