CaltechAUTHORS
  A Caltech Library Service

The Clusteron: Toward a Simple Abstraction for a Complex Neuron

Mel, Bartlett W. (1992) The Clusteron: Toward a Simple Abstraction for a Complex Neuron. In: Advances in Neural Information Processing Systems 4 (NIPS 1991). Advances in Neural Information Processing Systems . No.4. Morgan Kaufmann , San Mateo, CA, pp. 35-42. ISBN 1-55860-222-4. https://resolver.caltech.edu/CaltechAUTHORS:20160119-164727090

[img] PDF - Published Version
See Usage Policy.

1MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20160119-164727090

Abstract

Are single neocortical neurons as powerful as multi-layered networks? A recent compartmental modeling study has shown that voltage-dependent membrane nonlinearities present in a complex dendritic tree can provide a virtual layer of local nonlinear processing elements between synaptic inputs and the final output at the cell body, analogous to a hidden layer in a multi-layer network. In this paper, an abstract model neuron is introduced, called a clusteron, which incorporates aspects of the dendritic "cluster-sensitivity" phenomenon seen in these detailed biophysical modeling studies. It is shown, using a clusteron, that a Hebb-type learning rule can be used to extract higher-order statistics from a set of training patterns, by manipulating the spatial ordering of synaptic connections onto the dendritic tree. The potential neurobiological relevance of these higher-order statistics for nonlinear pattern discrimination is then studied within a full compartmental model of a neocortical pyramidal cell, using a training set of 1000 high-dimensional sparse random patterns.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://papers.nips.cc/paper/450-the-clusteron-toward-a-simple-abstraction-for-a-complex-neuronOrganizationArticle
Additional Information:© 1992 Morgan Kaufmann. This work was supported by the Office of Naval Research, the James McDonnell Foundation, and National Institute of Mental Health. Thanks to Christof Koch for providing an excellent working environment, Ken Miller for helpful discussions, and to Rodney Douglas for discussions and use of his neurons.
Funders:
Funding AgencyGrant Number
Office of Naval Research (ONR)UNSPECIFIED
James McDonnell FoundationUNSPECIFIED
National Institute of Mental Health (NIMH)UNSPECIFIED
Series Name:Advances in Neural Information Processing Systems
Issue or Number:4
Record Number:CaltechAUTHORS:20160119-164727090
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20160119-164727090
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:63785
Collection:CaltechAUTHORS
Deposited By:INVALID USER
Deposited On:20 Jan 2016 00:53
Last Modified:03 Oct 2019 09:31

Repository Staff Only: item control page