Principles and networks for self-organization in space-time

Authors:
Jose Principe;Neil Euliano;Shayan Garani
Affiliations:
Computational NeuroEngineering Laboratory, Department of Electrical Engineering, University of Florida, Gainesville, FL;NeuroDimension, Inc., 1800 N. Main Street, Gainesville, FL;Computational NeuroEngineering Laboratory, Department of Electrical Engineering, University of Florida, Gainesville, FL
Venue:
Neural Networks - New developments in self-organizing maps
Year:
2002

Citing 10
Cited 4

Higher order recurrent networks and grammatical inference

Advances in neural information processing systems 2
Storing temporal sequences

Neural Networks
Fundamentals of speech recognition

Fundamentals of speech recognition
The temporal Kohonen map

Neural Networks
1994 Special Issue: Diffusion-enhancement bilayer: Realizing long-range apparent motion and spatiotemporal grouping in a neural architecture

Neural Networks - Special issue: models of neurodynamics and behavior
Parallel hardware implementation of Kohonen's algorithm with an active medium

Neural Networks
Self-organizing maps

Self-organizing maps
Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM

Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM
Temporal self-organization for neural networks

Temporal self-organization for neural networks
Dynamic subgrouping in RTRL provides a faster O(N/sup 2/) algorithm

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 06

Dynamics and Topographic Organization of Recursive Self-Organizing Maps

Neural Computation
Self-organizing maps with refractory period

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Residual activity in the neurons allows SOMs to learn temporal order

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Self-Organizing neural networks for signal recognition

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we develop a spatio-temporal memory that blends properties from long and short-term memory and is motivated by reaction diffusion mechanisms. The winning processing element of a self-organizing network creates traveling waves on the output space that gradually attenuate over time and space to diffuse temporal information and create localized spatio-temporal neighborhoods for clustering. The novelty of the model is in the creation of time varying Voronoi tessellations anticipating the learned input signal dynamics even when the cluster centers are fixed. We test the method in a robot navigation task and in vector quantization of speech. This method performs better than conventional static vector quantizers based on the same data set and similar training conditions.