On the Performance of Pulsed and Spiking Neurons

  • Authors:
  • Leonardo Maria Reyneri

  • Affiliations:
  • Dipartimento di Elettronica, Politecnico di Torino

  • Venue:
  • Analog Integrated Circuits and Signal Processing
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

This tutorial paper presents an annotated overview of existing hardware implementations of Artificial Neural Systems based on “Pulse Stream” modulations, including also “Spiking Neurons.” Pulse Streams are quasi-periodic binary waveforms which convey analog information on waveform timing.The theoretical bases of Pulse Stream computation and multiplexing are shown for all the existing techniques. Pulse Stream modulations and multiplexing are then analyzed in terms of accuracy, response time, and both power and energy requirements. The performances of the various techniques are compared both with each other, and with those of other analog computing systems.