Zador, Anthony M. and Pearlmutter, Barak A. (1996) VC Dimension of an Integrate-and-Fire Neuron Model. Neural Computation, 8 (3). pp. 611-624. ISSN 0899-7667

Preview

Download (347kB) | Preview

Abstract

We compute the VC dimension of a leaky integrate-and-fire neuron model. The VC dimension quantifies the ability of a function class to partition an input pattern space, and can be considered a measure of computational capacity. In this case, the function class is the class of integrate-and-fire models generated by varying the integration time constant T and the threshold θ, the input space they partition is the space of continuous-time signals, and the binary partition is specified by whether or not the model reaches threshold at some specified time. We show that the VC dimension diverges only logarithmically with the input signal bandwidth N. We also extend this approach to arbitrary passive dendritic trees. The main contributions of this work are (1) it offers a novel treatment of computational capacity of this class of dynamic system; and (2) it provides a framework for analyzing the computational capabilities of the dynamic systems defined by networks of spiking neurons.

Item Type:	Article
Additional Information:	This is the postprint version of published article, which is available at doi:10.1162/neco.1996.8.3.611
Keywords:	VC Dimension; Integrate-and-Fire Neuron Model;
Academic Unit:	Faculty of Science and Engineering > Computer Science
Item ID:	8131
Identification Number:	https://doi.org/10.1162/neco.1996.8.3.611
Depositing User:	Barak Pearlmutter
Date Deposited:	07 Apr 2017 15:37
Journal or Publication Title:	Neural Computation
Publisher:	MIT Press
Refereed:	Yes
URI:	http://www.mitpressjournals.org
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads