Hebbian Learning using Fixed Weight Evolved Dynamical 'Neural' Networks

Izquierdo-Torres, Eduardo and Harvey, Inman (2007) Hebbian Learning using Fixed Weight Evolved Dynamical 'Neural' Networks. In: Proceedings of the First IEEE Symposium on Artificial Life. (IEEE-ALife'07), Hawaii.

Full text not available from this repository.


We evolve small continuous-time recurrent neural networks with fixed weights that perform Hebbian learning behavior. We describe the performance of the best and smallest successful system, providing an in-depth analysis of its evolved mechanisms. Learning is shown to arise from the interaction between the multiple timescale dynamics. In particular, we show how the fast-time dynamics alter the slow-time dynamics, which in turn shapes the local behavior around the equilibrium points of the fast components by acting as a parameter to them.

Item Type: Conference or Workshop Item (Paper)
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: Eduardo Jose Izquierdo-Torres
Date Deposited: 06 Feb 2012 18:12
Last Modified: 04 Apr 2012 12:23
URI: http://sro.sussex.ac.uk/id/eprint/15235
📧 Request an update