Unsupervised Learning of Temporal Sequences by Neural Networks
We propose to define a new model of formal neural network. This model extends existing Hopfield networks to process temporal data and achieve a non-supervised learning of them. We propose a learning law to adress in this context the sensitivity to input changes. A spatial representation of network’s temporal activity is given by which learnt sequences can be identified. An example of such a network is given and the results of the simulation are presented.
KeywordsInput Sequence Spike Train Temporal Sequence Spatial Representation Network Cell
Unable to display preview. Download preview PDF.
- B. Gas, R. Natowicz. A model of formal neural networks for unsupervised learning of binary temporal sequences. IJCNN, Baltimore (1992).Google Scholar
- B. Gas. Un modèle connexionniste non supervisé pour l’apprentissage et la reconnaissance de séquences tem-porelles. PhD thesis, Université de Paris X I (1994).Google Scholar
- B. Changeux. L’Homme Neuronal. Fayard 106, 110 (1983).Google Scholar