From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation

Soltoggio A, Stanley KO (2012)
Neural Networks 34: 28-41.

Journal Article | Published | English

No fulltext has been uploaded

Author
;
Abstract
Synaptic plasticity is a major mechanism for adaptation, learning, and memory. Yet current models struggle to link local synaptic changes to the acquisition of behaviors. The aim of this paper is to demonstrate a computational relationship between local Hebbian plasticity and behavior learning by exploiting two traditionally unwanted features: neural noise and synaptic weight saturation. A modulation signal is employed to arbitrate the sign of plasticity: when the modulation is positive, the synaptic weights saturate to express exploitative behavior; when it is negative, the weights converge to average values, and neural noise reconfigures the network's functionality. This process is demonstrated through simulating neural dynamics in the autonomous emergence of fearful and aggressive navigating behaviors and in the solution to reward-based problems. The neural model learns, memorizes, and modifies different behaviors that lead to positive modulation in a variety of settings. The algorithm establishes a simple relationship between local plasticity and behavior learning by demonstrating the utility of noise and weight saturation. Moreover, it provides a new tool to simulate adaptive behavior, and contributes to bridging the gap between synaptic changes and behavior in neural computation. (C) 2012 Elsevier Ltd. All rights reserved.
Publishing Year
ISSN
PUB-ID

Cite this

Soltoggio A, Stanley KO. From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation. Neural Networks. 2012;34:28-41.
Soltoggio, A., & Stanley, K. O. (2012). From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation. Neural Networks, 34, 28-41.
Soltoggio, A., and Stanley, K. O. (2012). From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation. Neural Networks 34, 28-41.
Soltoggio, A., & Stanley, K.O., 2012. From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation. Neural Networks, 34, p 28-41.
A. Soltoggio and K.O. Stanley, “From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation”, Neural Networks, vol. 34, 2012, pp. 28-41.
Soltoggio, A., Stanley, K.O.: From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation. Neural Networks. 34, 28-41 (2012).
Soltoggio, Andrea, and Stanley, Kenneth O. “From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation”. Neural Networks 34 (2012): 28-41.
This data publication is cited in the following publications:
This publication cites the following data publications:

3 Citations in Europe PMC

Data provided by Europe PubMed Central.

Rare neural correlations implement robotic conditioning with delayed rewards and disturbances.
Soltoggio A, Lemme A, Reinhart F, Steil JJ., Front Neurorobot 7(), 2013
PMID: 23565092
Solving the distal reward problem with rare correlations.
Soltoggio A, Steil JJ., Neural Comput 25(4), 2013
PMID: 23339615

Export

0 Marked Publications

Open Data PUB

Web of Science

View record in Web of Science®

Sources

PMID: 22796669
PubMed | Europe PMC

Search this title in

Google Scholar