A Model for Fast Analog Computations with Noisy Spiking Neurons
We show that networks of spiking neurons can simulate arbitrary feedforward sigmoidal neural nets in a way which has previously not been considered. This new approach is based on temporal coding by single spikes (respectively by the timing of synchronous firing in pools of neurons), rather than on the traditional interpretation of analog variables in terms of firing rates.
As a consequence we can show that networks of noisy spiking neurons are “universal approximators” in the sense that they can approximate with regard to temporal coding any given continuous function of several variables.
KeywordsActivation Function Firing Rate Neural Information Processing System Dendritic Tree Firing Time
Unable to display preview. Download preview PDF.
- Gerstner, W. and van Hemmen, J. L. (1994) How to describe neuronal activity: spikes, rates, or assemblies? Advances in Neural Information Processing Systems, vol. 6, Morgan Kaufmann (San Mateo) 463–470.Google Scholar
- Hopfield, J. J. (1991) Olfactory computation and object perception. Proc. Nat. Ac. Sci. USA, vol. 88, 6462–6466.Google Scholar
- Hopfield, J. J. (1995) Pattern recognition computation using action potential timing for stimulus representations. Nature, vol. 376, 33–36.Google Scholar
- Leshno, M., Lin, V. Y., Pinkus, A., and Schocken, S. (1993) Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks, vol. 6, 861–867.Google Scholar
- Linsker, R. (1988) Self-organization in a perceptual network. Computer Magazine, vol. 21, 105–117.Google Scholar
- Maass, W. (1995) Fast sigmoidal networks via noisy spiking neurons,to appear in Neural Computation.Google Scholar
- Maass, W. (1996) On the computational power of noisy spiking neurons. Advances in Neural Information Processing Systems, vol. 8, MIT-Press (Cambridge), 211–217.Google Scholar
- Mainen, Z.F. and Sejnowski, T. J. (1995) Reliability of spike timing in neocortical neurons. Science, vol. 268, 1503–1506.Google Scholar
- Markram, H. and Sakmann, B. (1995) Action potentials propagating back into dendrites trigger changes in efficacy of single-axon synapses between layer V pyramidal neurons. Abstract 788.11 in Vol. 21 of the Proc. of the Conference of the Society for Neuroscience.Google Scholar
- Mel, B. W. (1993) Synaptic integration in an excitable dendritic tree. J. of Neurophysiology, vol. 70, 1086–1101.Google Scholar
- Rolls, E. T. (1994a) Brain mechanisms for invariant visual recognition and learning. Behavioural Processes, vol. 33, 113–138.Google Scholar
- Rolls, E. T. and Tovee, M. J. (1994b) Processing speed in the cerebral cortex, and the neurophysiology of visual backward masking. Proc. Roy. Soc. B., vol. 257, 9–15.Google Scholar
- Shepherd, G. M. (1994) Neurobiology,3rd ed. Oxford University Press (New York).Google Scholar
- Thorpe, S. J. and Imbert, M. (1989) Biological constraints on connectionist modelling. In: Connectionism in Perspective, Pfeifer, R., Schreter, Z., Fogelman-Soulié, F., and Steels, L., eds., Elsevier (North-Holland).Google Scholar