Title :
Statistical approach to unsupervised recognition of spatio-temporal patterns by spiking neurons
Author_Institution :
Megaputer Intelligence Ltd, Moscow, Russia
Abstract :
The problem of unsupervised recognition of spatio-temporal structure in the sensory signal by a network of spiking neurons is considered from the statistical point of view. A novel model of spiking neurons called SSN/st is proposed as a solution for this problem. Computational experiments with artificially generated data demonstrate that statistically sound unsupervised learning mechanism and generalized Hebbian laws of synaptic plasticity implemented in this model provide it with high sensitivity and robustness.
Keywords :
Hebbian learning; medical signal processing; neural nets; pattern recognition; statistical analysis; unsupervised learning; SSN/st; artificially generated data; generalized Hebbian laws; sensory signal; spiking neurons; statistical approach; synaptic plasticity; unsupervised learning mechanism; unsupervised spatio-temporal pattern recognition; Acoustic noise; Artificial neural networks; Biological neural networks; Brain modeling; Character recognition; Equations; Learning systems; Neurons; Noise level; Pattern recognition;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1224022
