Unsupervised Extraction of Structural Information from HighDimensional Visual Data

Authors:
Stephen McGlinchey;Darryl Charles;Pei Ling Lai;Colin Fyfe
Affiliations:
Applied Computational Intelligence Research Unit, University of Paisley, Paisley, Scotland;Applied Computational Intelligence Research Unit, University of Paisley, Paisley, Scotland;Applied Computational Intelligence Research Unit, University of Paisley, Paisley, Scotland;Applied Computational Intelligence Research Unit, University of Paisley, Paisley, Scotland
Venue:
Applied Intelligence
Year:
2000

Citing 5
Cited 0

Representation and separation of signals using nonlinear PCA type learning

Neural Networks
A multiple cause mixture model for unsupervised learning

Neural Computation
Self-organized formation of various invariant-feature filters in the adaptive-subspace SOM

Neural Computation
Sparse coding in the primate cortex

The handbook of brain theory and neural networks
Recognition of human head orientation based on artificial neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present three unsupervised artificial neural networksfor the extraction of structural information from visual data. Theability of each network to represent structured knowledge in a mannereasily accessible to human interpretation is illustrated usingartificial visual data. These networks are used to collectivelydemonstrate a variety of unsupervised methods for identifyingfeatures in visual data and the structural representation of thesefeatures in terms of orientation, temporal and topographicalordering, and stereo disparity.