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

    Authors

    A. Soltoggio;K. O. Stanley

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    Neural Netw.

    Keywords

    Adaptive behavior; Computational models; Learning; Neural plasticity; Neuromodulation; DEPENDENT SYNAPTIC PLASTICITY; HETEROSYNAPTIC FACILITATION; UNCERTAIN; ENVIRONMENTS; FEEDFORWARD INHIBITION; NEURAL-NETWORKS; IN-VITRO; REWARD; DOPAMINE; NEUROMODULATION; SYNAPSES; Computer Science, Artificial Intelligence; Neurosciences

    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.

    Journal Title

    Neural Networks

    Volume

    34

    Publication Date

    1-1-2012

    Document Type

    Article

    Language

    English

    First Page

    28

    Last Page

    41

    WOS Identifier

    WOS:000308842300004

    ISSN

    0893-6080

    Share

    COinS