Learning to generalize from single examples in the dynamic link architecture

Authors:
Wolfgang Konen;Christoph von der Malsburg
Affiliations:
Institut für Neuroinfomatik, Ruhr-Universität Bochum, Germany;Institut für Neuroinfomatik, Ruhr-Universität Bochum, Germany
Venue:
Neural Computation
Year:
1993

Citing 3
Cited 2

Learning symmetry groups with hidden units: beyond the perceptron

Physica D
Object recognition with Gabor functions in the dynamic link architecture: parallel implementation on a transputer network

Neural networks for signal processing
Distortion Invariant Object Recognition in the Dynamic Link Architecture

IEEE Transactions on Computers

1994 Special Issue: A fast dynamic link matching algorithm for invariant pattern recognition

Neural Networks - Special issue: models of neurodynamics and behavior
Symmetry Detection Using Global-Locally Coupled Maps

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A large attraction of neural systems lies in their promise of replacing programming by learning. A problem with many current neural models is that with realistically large input patterns learning time explodes. This is a problem inherent in a notion of learning that is based almost entirely on statistical estimation. We propose here a different learning style where significant relations in the input pattern are recognized and expressed by the unsupervised self-organization of dynamic links. The power of this mechanism is due to the very general a priori principle of conservation of topological structure. We demonstrate that style with a system that learns to classify mirror symmetric pixel patterns from single examples.