From Spiking Neurons to Dynamic Perceptrons
This paper begins a systematic validation for a simple and reliable artificial neural network model that can be directly related to the main behaviour of biological neural networks. The sigmoid-plus-linear filter appears to be a promising candidate if the sigmoidal function is calculated in reference to the pulse generation refractory effects. We directly compare a classical spiking neuron model with a scheme based on a sigmoidal function plus a linear filter. The filter is computed as the best least squares fit to the output of the spiking model. The results seem to confirm that FIR and IIR neural networks may be able to represent the essence of the signal processing performed by biological neurons.
Unable to display preview. Download preview PDF.
- A.B. Carlson. Communication Systems. Prentice-Hall, 1986. Third Edition.Google Scholar
- C.E. Carr and M. Konishi. A circuit for the detection of intereaural time differences in the brain stem of the barn owl. J. Neuroscience, 10:3227–3246, 1990.Google Scholar
- D. Ferster and N. Spruston. Cracking the neuronal code. Science, 270:756–757, November 1995.Google Scholar
- S. Haykin. Adaptive Filter Theory. Prentice-Hall, New York, 1996. Third Edition.Google Scholar
- S. Haykin. Neural Networks: A Comprehensive Foundation. Prentice-Hall, New York, 1998. Second Edition.Google Scholar
- C. Koch and I. Seger. Methods in Neural Modeling. MIT Press, Cambridge, MA, 1989.Google Scholar
- A. Moiseff and M. Konishi. Binaural characteristics of units in the owl’s brainstem auditory pathway: Precursors of restrictive spatial receptive fields. J. Neuroscience, 3:2353–2362, 1983.Google Scholar
- S.A. Shamma. Spatial and temporal processing in central auditory systems. In C. Koch and I. Seger, editors, Methods in Neural Modeling, pages 247–289. MIT Press, Cambridge, MA, 1989.Google Scholar
- H.C. Tuckwell. Introduction to Theoretical Neurobiology: Nonlinear and Stochastic Theories, volume 2. 1988.Google Scholar