Associative learning on a continuum in evolved dynamical networks

Izquierdo, Eduardo, Harvey, Inman and Beer, Randall D (2008) Associative learning on a continuum in evolved dynamical networks. Adaptive Behavior, 16 (6). pp. 361-384. ISSN 1059-7123

Full text not available from this repository.


This article extends previous work on evolving learning without synaptic plasticity from discrete tasks to continuous tasks. Continuous-time recurrent neural networks without synaptic plasticity are artificially evolved on an associative learning task. The task consists in associating paired stimuli: temperature and food. The temperature to be associated can be either drawn from a discrete set or allowed to range over a continuum of values. We address two questions: Can the learning without synaptic plasticity approach be extended to continuous tasks? And if so, how does learning without synaptic plasticity work in the evolved circuits? Analysis of the most successful circuits to learn discrete stimuli reveal finite state machine (FSM) like internal dynamics. However, when the task is modified to require learning stimuli on the full continuum range, it is not possible to extract a FSM from the internal dynamics. In this case, a continuous state machine is extracted instead

Item Type: Article
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: Eduardo Jose Izquierdo-Torres
Date Deposited: 06 Feb 2012 21:26
Last Modified: 28 Mar 2012 13:38
📧 Request an update