Evolution of Multisensory Integration in Large Neural Fields

  • Benjamin Inden
  • Yaochu Jin
  • Robert Haschke
  • Helge Ritter
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7401)


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.


Connection Weight Multisensory Integration Lateral Connection Connection Gene Evolutionary Robotic 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Spence, C.: Multisensory integration, attention and perception. In: Signals and Perception — The Fundamentals of Human Sensation, pp. 345–354. Palgrave Macmillan (2002)Google Scholar
  2. 2.
    Stein, B.E., Stanford, T.R.: Multisensory integration: current issues from the perspective of the single neuron. Nature Rewievs Neuroscience 9, 255–266 (2008)CrossRefGoogle Scholar
  3. 3.
    Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evolutionary Intelligence 1, 47–62 (2008)CrossRefGoogle Scholar
  4. 4.
    Nolfi, S., Floreano, D.: Evolutionary Robotics — The Biology, Intelligence, and Technology of Self-Organizing Machines. MIT Press (2000)Google Scholar
  5. 5.
    Inden, B., Jin, Y., Haschke, R., Ritter, H.: Neatfields: Evolution of neural fields. In: Proceedings of the Conference on Genetic and Evolutionary Computation (2010)Google Scholar
  6. 6.
    Inden, B., Jin, Y., Haschke, R., Ritter, H.: How evolved neural fields can exploit inherent regularity in multilegged robot locomotion tasks. In: Third World Congres on Nature and Biologically Inspired Computation (2011)Google Scholar
  7. 7.
    Inden, B., Jin, Y., Haschke, R., Ritter, H.: Evolving neural fields for problems with large input and output spaces. Neural Networks 28, 24–39 (2012)CrossRefGoogle Scholar
  8. 8.
    Westermann, G.: A model of perceptual change by domain integration. In: Proceedings of the 23rd Annual Conference of the Cognitive Science Society (2001)Google Scholar
  9. 9.
    Stanley, K., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10, 99–127 (2002)CrossRefGoogle Scholar
  10. 10.
    Ruppin, E.: Evolutionary autonomous agents: A neuroscience perspective. Nature Reviews Neuroscience 3, 132–141 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Benjamin Inden
    • 1
  • Yaochu Jin
    • 2
  • Robert Haschke
    • 3
  • Helge Ritter
    • 3
  1. 1.Research Institute for Cognition and RoboticsBielefeld UniversityGermany
  2. 2.Department of ComputingUniversity of SurreyUK
  3. 3.Neuroinformatics GroupBielefeld UniversityGermany

Personalised recommendations