Learning on a Continuum in Evolved Dynamical Node Networks

Izquierdo-Torres, Eduardo and Harvey, Inman (2006) Learning on a Continuum in Evolved Dynamical Node Networks. In: Artificial Life X, Proceedings of the Tenth International Conference on the Simulation and Synthesis of Living Systems, Bloomington, Indiana, USA.

Full text not available from this repository.


In artificial life, there has been much previous research using evolution to generate learning behaviour within dynamical system controllers without pre-defining the learning mechanisms; so far this research has focused exclusively on evolving agents that can behave differently in a discrete number of different scenarios, generally two. But many (arguably most) interesting discrimination tasks in real life are where the scenarios are over a continuum; one example would be parental imprinting in birds. Here we analyse a successfully evolved embodied and situated agent on an abstract model of this imprinting and give the first published example of such learning on a continuum.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Originality. First use of this method to successfully discriminate over a continuum. Rigour. Evolutionary robotics applied to discrimination tasks. Significance.This opens up a new range of experimental areas. Outlet/Citations. Top ranking Intl conference in the area.
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: Inman Harvey
Date Deposited: 06 Feb 2012 20:19
Last Modified: 13 Apr 2012 14:38
URI: http://sro.sussex.ac.uk/id/eprint/25434
📧 Request an update