Evolution of multisensory integration in large neural fields

Authors:
Benjamin Inden;Yaochu Jin;Robert Haschke;Helge Ritter
Affiliations:
Research Institute for Cognition and Robotics, Bielefeld University, Germany;Department of Computing, University of Surrey, UK;Neuroinformatics Group, Bielefeld University, Germany;Neuroinformatics Group, Bielefeld University, Germany
Venue:
EA'11 Proceedings of the 10th international conference on Artificial Evolution
Year:
2011

Citing 4
Cited 1

Evolutionary Robotics: The Biology,Intelligence,and Technology

Evolutionary Robotics: The Biology,Intelligence,and Technology
Evolving neural networks through augmenting topologies

Evolutionary Computation
NEATfields: evolution of neural fields

Proceedings of the 12th annual conference on Genetic and evolutionary computation
Evolving neural fields for problems with large input and output spaces

Neural Networks

Evolving neural fields for problems with large input and output spaces

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We show that by evolving neural fields it is possible to study the evolution of neural networks that perform multisensory integration of high dimensional input data. In particular, four simple tasks for the integration of visual and tactile input are introduced. Neural networks evolve that can use these senses in a cost-optimal way, enhance the accuracy of classifying noisy input images, or enhance spatial accuracy of perception. An evolved neural network is shown to display a kind of McGurk effect.