Perceptual Binding by Coupled Oscillatory Neural Network
The binding problem is a problem on the integration of perceptual properties in our brains. For describing this problem in the artificial neural network, it is necessary to introduce the temporal coding of information. In this paper, we propose a neural network model that can represent the bindings of external stimuli, based on the network that is capable of figure-ground segmentation proposed by Sompolinsky and Tsodyks. This model adopts the coupled oscillators that can represent the temporal coding and the synchronization among them.
KeywordsNeural Network Model Couple Oscillatory Color Network Input Stimulus Temporal Code
Unable to display preview. Download preview PDF.
- 2.van der Malsburg, C.: The correlation theory of brain function. Technical Report 81-2, Max-Planck-Institute for Biophysical Chemistry (1981)Google Scholar
- 5.Wennekers, T., Palm, G.: On the relation between neural modelling and experimental neuroscience. Theory in Biosciences 116, 273–289 (1997)Google Scholar
- 7.van der Malsburg, C.: The what and why of binding: The modeler’s perspective. Neuron, 95–104 (1999)Google Scholar
- 8.Abott, L., Sejowski, T.J.: Neural Codes and Distributed Representation. MIT Press, Cambridge (1999)Google Scholar