NEATfields: Evolution of neural fields for visual discrimination and multiple pole balancing tasks
Inden, B, Jin, Y, Haschke, R and Ritter, H (2010) NEATfields: Evolution of neural fields for visual discrimination and multiple pole balancing tasks In: Genetic and Evolutionary Computation Conference, 2010-07-07 - ?, Portland.
Available under License : See the attached licence file.
We have developed a novel extension of the NEAT neuroevolution method, termed NEATfields, to solve problems with large input and output spaces. NEATfields networks are layered into two-dimensional fields of identical or similar subnetworks with an arbitrary topology. The subnetworks are evolved with genetic operations similar to those used in the NEAT neuroevolution method. We show that information processing within the neural fields can be organized by providing suitable building blocks to evolution. NEATfields can solve a number of visual discrimination tasks and a newly introduced multiple pole balancing task.
|Item Type:||Conference or Workshop Item (Paper)|
|Additional Information:||Copyright 2010 The authors|
|Divisions:||Faculty of Engineering and Physical Sciences > Computing Science|
|Depositing User:||Symplectic Elements|
|Date Deposited:||22 Jun 2012 17:23|
|Last Modified:||23 Sep 2013 19:27|
Actions (login required)
Downloads per month over past year