Reduction of Visual Information in Neural Network Learning Visualization

Authors:
Matúš Užák;Rudolf Jakša;Peter Sinčák
Affiliations:
Center for Intelligent Technologies Department of Cybernetics and Artificial Intelligence, Technical University of Košice, Slovakia;Center for Intelligent Technologies Department of Cybernetics and Artificial Intelligence, Technical University of Košice, Slovakia;Center for Intelligent Technologies Department of Cybernetics and Artificial Intelligence, Technical University of Košice, Slovakia
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 3
Cited 0

Self-organized formation of topologically correct feature maps

Neurocomputing: foundations of research
A Self-Organizing Network that Can Follow Non-stationary Distributions

ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Framework for the interactive learning of artificial neural networks

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

Visualization of neural network learning faces the problem of overwhelming amount of visual information. This paper describes the application of clustering methods for reduction of visual information in the response function visualization. If only clusters of neurons are visualized instead of direct visualization of responses of all neurons in the network, the amount of visually presented information can be significantly reduced. This is useful for user fatigue reduction and also for minimization of the visualization equipment requirements. We show that application of Kohonen network or Growing Neural Gas with Utility Factor algorithm allows to visualize the learning of moderate-sized neural networks. Comparison of both algorithms in this task is provided, also with performance analysis and example results of response function visualization.