A multimodal self-organizing network for sensory integration of letters and phonemes

Authors:
Lennart Gustafsson;Tamas Jantvik;Andrew P. Papliński
Affiliations:
Luleå University of Technology, Luleå, Sweden;Luleå University of Technology, Luleå, Sweden;Monash University, Melbourne, Victoria, Australia
Venue:
ASC '07 Proceedings of The Eleventh IASTED International Conference on Artificial Intelligence and Soft Computing
Year:
2007

Citing 7
Cited 1

The 'Neural' Phonetic Typewriter

Computer
Self-Organizing Maps

Self-Organizing Maps
Reading Speech from Still and Moving Faces: The Neural Substrates of Visible Speech

Journal of Cognitive Neuroscience
Neural Specialization for Letter Recognition

Journal of Cognitive Neuroscience
The Fusiform "Face Area" is Part of a Network that Processes Faces at the Individual Level

Journal of Cognitive Neuroscience
Multimodal feedforward self-organizing maps

CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part I
Feedback in multimodal self-organizing networks enhances perception of corrupted stimuli

AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence

A self-organized artificial neural network architecture for sensory integration with applications to letter-phoneme integration

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Integration of signals from sensory receptors of different modalities is known to enhance perception. Integration takes place in bimodal and multimodal association areas of neocortex and results in robust bimodal or multimodal percepts as well as in feedback mediated enhanced unimodal perception. A Multimodal Self-Organizing Network, MuSON, is presented as a tool for simulating sensory integration. The latest version of this MuSON, that is described in the current paper, also takes the degree of recognition of stimuli in the various maps of the network into account. Simulation results show the same characteristics as corresponding results from psychology and neuroscience.