GTM: the generative topographic mapping
Neural Computation
Kalman filter implementation of self-organizing feature maps
Neural Computation
SOAN: Self Organizing with Adaptive Neighborhood Neural Network
IWANN '99 Proceedings of the International Work-Conference on Artificial and Natural Neural Networks: Foundations and Tools for Neural Modeling
Recursive self-organizing maps
Neural Networks - New developments in self-organizing maps
TASOM: a new time adaptive self-organizing map
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
The parameterless self-organizing map algorithm
IEEE Transactions on Neural Networks
A model of task-specific focal dystonia
Neural Networks
Hi-index | 0.00 |
T. Kohonen's self organizing map (SOM) may be considered as a plausible structure for modelling pattern recognition processes in the brain. Neighborhood preservation corresponds closely to what is called somatotopy in the neurosciences, and the context specificity of mappings observed (e. g. in malfunctions of the brain) becomes easily explicable in the framework of the SOM. However, there are two features which impair the aptitude of the classical SOM for neurophysiological models: the adaptation procedure is explicitly time dependent and the procedure consumes the whole set of disposable neurons. Because of the latter property, a SOM cannot learn different tasks, adapting one subset of neurons to a data set X^1 and another to a subsequently presented data set X^2 . The present paper describes a modified SOM which avoids the drawbacks mentioned above. Its adaptation procedure is time independent. When the training sequence consists of data from successive data clusters X^k each cluster is mapped to a subset G^k of the neuron set G while the other neurons are left almost unchanged. The behavior of the resulting DCNG-SOM is demonstrated in several experiments.