A Flexible Hardware Architecture for Online Hebbian Learning in the Sender-Oriented PCNN-Neurocomputer Spike 128K

  • Authors:
  • Martin Schgfer;Georg Hartmann

  • Affiliations:
  • -;-

  • Venue:
  • MICRONEURO '99 Proceedings of the 7th International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we describe a hardware-architecture that provides online hebbian learning for PCNNs according to different learning-rules. This architecture is an extension of the Spike 128K-system which is shortly introduced, focusing the sender-oriented structure of the entire system. The algorithms derived for three well proved Hebbian learning-rules are compatible with this sender-oriented structure. The introduced architecture integrates processing of these learning-rules very efficiently into the Spike 128K-system.