Elsevier

Neural Networks

Volume 10, Issue 9, December 1997, Pages 1659-1671
Neural Networks

Contributed article
Networks of spiking neurons: The third generation of neural network models

https://doi.org/10.1016/S0893-6080(97)00011-7Get rights and content

Abstract

The computational power of formal models for networks of spiking neurons is compared with that of other neural network models based on McCulloch Pitts neurons (i.e., threshold gates), respectively, sigmoidal gates. In particular it is shown that networks of spiking neurons are, with regard to the number of neurons that are needed, computationally more powerful than these other neural network models. A concrete biologically relevant function is exhibited which can be computed by a single spiking neuron (for biologically reasonable values of its parameters), but which requires hundreds of hidden units on a sigmoidal neural net. On the other hand, it is known that any function that can be computed by a small sigmoidal neural net can also be computed by a small network of spiking neurons. This article does not assume prior knowledge about spiking neurons, and it contains an extensive list of references to the currently available literature on computations in networks of spiking neurons and relevant results from neurobiology.

References (74)

  • M.A. Arbib
  • W. Bair et al.

    Reliable temporal modulation in cortical spike trains in the awake monkey

  • E. Bienenstock

    A model of neocortex

    Network: Computation in Neural Systems

    (1995)
  • J.M. Bower et al.

    The book of GENESIS: exploring realistic neural models with the General Neural Simulation System

    (1995)
  • P.S. Churchland et al.

    The computational brain

    (1993)
  • M.C. Crair et al.

    Non-Boltzmann dynamics in networks of spiking neurons

  • B. DasGupta et al.

    The power of approximating: a comparison of activation functions

  • M.R. DeYong et al.

    The design, fabrication, and test of a new VLSI hybrid analog-digital neural processing element

    IEEE Transcripts on Neural Networks

    (1992)
  • R.J. Douglas et al.

    Recurrent excitation in neocortical circuits

    Science

    (1995)
  • D. Ferster et al.

    Cracking the neuronal code

    Science

    (1995)
  • W. Gerstner

    Associative memory in a network of “biological neurons”

  • W. Gerstner

    Time structure of the activity in neural network models

    Physics Review E

    (1995)
  • W. Gerstner et al.

    How to describe neuronal activity: spikes, rates, or assemblies

  • W. Gerstner et al.

    A biologically motivated and analytically soluble model of collective oscillations in the cortex: I. Theory of weak locking

    Biological Cybernetics

    (1993)
  • P.W. Goldberg et al.

    Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers

    Machine Learning

    (1995)
  • Herrmann, M., Hertz, J. A., & Prügel-Bennett, A. (in press). Analysis of synfire chains. Nordita...
  • J.J. Hopfield

    Pattern recognition computation using action potential timing for stimulus representations

    Nature

    (1995)
  • J.J. Hopfield et al.

    Rapid local synchronization of action potentials: towards computation with coupled integrate-and-fire neurons

  • T. Horinchi et al.

    A delay-line based motion detection chip

  • A. Jahnke et al.

    A SIMD/dataflow architecture for a neurocomputer for spike-processing neural networks (NESPINN)

    MicroNeuro

    (1996)
  • C.T. Jiu et al.

    An analog VLSI time-encoded pattern classifier

  • D. Johnston et al.

    Foundations of cellular neurophisiology

    (1995)
  • Karpinski, M., & Macintyre, A. (in press). Polynomial bounds for VC-dimension of sigmoidal and general Pfaffian neural...
  • R. Kempter et al.

    Temporal coding in the sub-millisecond range: model of barn owl auditory pathway

  • C. Koch et al.

    Multiplying with synapses and neurons

  • P. Koiran

    VC-dimension in circuit complexity

  • J. Krüger et al.

    Multielectrode investigation of monkey striate cortex: spike train correlations in the infragranular layers

    Journal of Neurophysiology

    (1988)
  • Cited by (2401)

    View all citing articles on Scopus
    View full text