June 2006
Volume 6, Issue 6
Free
Vision Sciences Society Annual Meeting Abstract  |   June 2006
Visual segmentation in a biomorphic neural network
Author Affiliations
  • Stefan Roth
    Institute of Neuroinformatics, University and ETH, Zurich
  • Daniel Kiper
    Institute of Neuroinformatics, University and ETH, Zurich
  • Paul F. M. J. Verschure
    Institute of Neuroinformatics, University and ETH, Zurich
Journal of Vision June 2006, Vol.6, 888. doi:10.1167/6.6.888
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Stefan Roth, Daniel Kiper, Paul F. M. J. Verschure; Visual segmentation in a biomorphic neural network. Journal of Vision 2006;6(6):888. doi: 10.1167/6.6.888.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Based on our earlier work on the encoding of complex stimuli by cortical networks (Wyss et al., 2003) we designed a neural network to classify visual stimuli. The transmission delays of the connections among the excitatory neurons, which are proportional to length, result in a complex spatial and temporal activity pattern when a visual stimulus is presented to the network. The pooled neuronal activity, or temporal population code - TPC, represents a stimulus-specific fingerprint that is invariant to translations, rotations, and small distortions. The TPC thus allows a highly accurate and robust stimulus classification in situations where a single target is presented to the network. However, classification fails when the scene also includes a closely positioned distractor. We show here that by introducing dendritic attenuation in the model, we are able to increase classification performance in the presence of a distractor, i.e. segmentation. Moreover, by combining codes of several attenuation levels, we obtain a segmentation model that is robust and scalable both with and without distractor. Hence, our results suggest that both dense lateral connectivity and dendritic structure provide a complementary computational substrate for the encoding of complex stimuli.

This project is supported by the Swiss Federal Institute of Technology (ETH) Zurich.

Roth, S. Kiper, D. Verschure, P. F. M. J. (2006). Visual segmentation in a biomorphic neural network [Abstract]. Journal of Vision, 6(6):888, 888a, http://journalofvision.org/6/6/888/, doi:10.1167/6.6.888. [CrossRef]
×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×