TurSOM: a turing inspired self-organizing map

Authors:
Derek Beaton;Iren Valova;Dan MacLean
Affiliations:
James J. Kaput Center for Research and Innovation in Mathematics Education, University of Massachusetts Dartmouth, Fairhaven, MA;Department of Computer and Information Science, University of Massachusett Dartmouth, North Dartmouth, MA;Computer and Information Science Department, University of Massachusett Dartmouth, North Dartmouth, MA
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 6
Cited 2

Self-organizing maps

Self-organizing maps
Measures for the organization of self-organizing maps

Self-Organizing neural networks
Identification of Patterns via Region-Growing Parallel SOM Neural Network

ICMLA '08 Proceedings of the 2008 Seventh International Conference on Machine Learning and Applications
A parallel growing architecture for self-organizing maps with unsupervised learning

Neurocomputing
CQoCO: A measure for comparative quality of coverage and organization for self-organizing maps

Neurocomputing
Fractal initialization for high-quality mapping with self-organizing maps

Neural Computing and Applications

Growing mechanisms and cluster identification with TurSOM

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
TurSOM: A paradigm bridging Turing's unorganized machines and self-organizing maps demonstrating dual self-organization

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

TurSOM [1], short for Turing Self-Organizing Map, introduces new concepts, responsibilities and mechanisms to the traditional SOM algorithm. It draws its inspiration from Turing Unorganized Machines, competitive learning techniques, and SOM algorithms. Turing's unorganized machines (TUM) were one of the first computational concepts of modeling the cortex. Turing also described these machines as having self-organizing behaviors. The primary difference between Turing's self-organization description, and more traditional models we are familiar with (Grossberg, Kohonen), are that connections, rather than neurons, self-organize. TurSOM adheres to unsupervised, competitive learning techniques, wherein all neurons, and all connections between them are self-organizing and competing. As such, it presents a novel self-organizing neural network algorithm that eliminates the need for post-processing methods for cluster identification.