Mechanical intelligence (collected works of A. M. Turing)
Mechanical intelligence (collected works of A. M. Turing)
Topology representing networks
Neural Networks
Clustering of EEG-Segments Using Hierarchical Agglomerative Methods and Self-Organizing Maps
ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Student Modeling Using Principal Component Analysis of SOM Clusters
ICALT '04 Proceedings of the IEEE International Conference on Advanced Learning Technologies
Identification of Patterns via Region-Growing Parallel SOM Neural Network
ICMLA '08 Proceedings of the 2008 Seventh International Conference on Machine Learning and Applications
TurSOM: a turing inspired self-organizing map
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Growing mechanisms and cluster identification with TurSOM
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
The Computer Journal
Fractal initialization for high-quality mapping with self-organizing maps
Neural Computing and Applications
Topology preservation in self-organizing feature maps: exact definition and measurement
IEEE Transactions on Neural Networks
Quantifying the neighborhood preservation of self-organizing feature maps
IEEE Transactions on Neural Networks
Hi-index | 0.01 |
Self-organization is a widely used technique in unsupervised learning and data analysis, largely exemplified by k-means clustering, self-organizing maps (SOM) and adaptive resonance theory. In this paper we present a new algorithm: TurSOM, inspired by Turing's unorganized machines and Kohonen's SOM. Turing's unorganized machines are an early model of neural networks characterized by self-organizing connections, as opposed to self-organizing neurons in SOM. TurSOM introduces three new mechanisms to facilitate both neuron and connection self-organization. These mechanisms are: a connection learning rate, connection reorganization, and a neuron responsibility radius. TurSOM is implemented in a 1-dimensional network (i.e. chain of neurons) to exemplify the theoretical implications of these features. In this paper we demonstrate that TurSOM is superior to the classical SOM algorithm in several ways: (1) speed until convergence; (2) independent clusters; and (3) tangle-free networks.