Investigating learning parameters in a standard 2-d SOM model to select good maps and avoid poor ones

Authors:
Hiong Sen Tan;Susan E. George
Affiliations:
University of South Australia, Mawson Lakes, SA, Australia;University of South Australia, Mawson Lakes, SA, Australia
Venue:
AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
Year:
2004

Citing 7
Cited 2

Neural networks: algorithms, applications, and programming techniques

Neural networks: algorithms, applications, and programming techniques
Growing cell structures—a self-organizing network for unsupervised and supervised learning

Neural Networks
Essence of Neural Networks

Essence of Neural Networks
Self-Organizing Maps

Self-Organizing Maps
Comparing Self-Organizing Maps

ICANN 96 Proceedings of the 1996 International Conference on Artificial Neural Networks
Auto-SOM: Recursive Parameter Estimation for Guidance of Self-Organizing Feature Maps

Neural Computation
Dynamic self-organizing maps with controlled growth for knowledge discovery

IEEE Transactions on Neural Networks

Neural unit shape representation: A new SOM-based visualisation

International Journal of Knowledge-based and Intelligent Engineering Systems
Influence of learning rates and neighboring functions on self-organizing maps

WSOM'11 Proceedings of the 8th international conference on Advances in self-organizing maps

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the self organising map (SOM), applying different learning parameters to the same input will lead to different maps The question of how to select the best map is important A map is good if it is relatively accurate in representing the input and ordered A measure or measures are needed to quantify the accuracy and the ‘order' of maps This paper investigates the learning parameters in standard 2- dimensional SOMs to find the learning parameters that lead to optimal arrangements An example of choosing a map in a real world application is also provided.