Evolution of bilateral symmetry in agents controlled by spiking neural networks

We present in this paper three novel developmental models allowing information to be encoded in space and time, using spiking neurons placed on a 2D substrate. In two of these models, we introduce neural development that can use bilateral symmetry. We show that these models can create neural control...

Full description

Saved in:
Bibliographic Details
Main Authors: Oros, N., Steuber, V., Davey, N., Canamero, L., Adams, R.
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Context modeling
Encoding
Evolutionary computation
Genetic algorithms
Humans
Neural networks
Neurons
Organisms
Space technology
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present in this paper three novel developmental models allowing information to be encoded in space and time, using spiking neurons placed on a 2D substrate. In two of these models, we introduce neural development that can use bilateral symmetry. We show that these models can create neural controllers for agents evolved to perform chemotaxis. Neural bilateral symmetry can be evolved and be beneficial for an agent. This work is the first, as far as we know, to present developmental models where spiking neurons are generated in space and where bilateral symmetry can be evolved and proved to be beneficial in this context.
ISSN:2160-6374
2160-6382
DOI:10.1109/ALIFE.2009.4937702