Extending discrete Hopfield networks for unsupervised learning of temporal sequences

We propose to define a new model of formal neural network. This model extends existing Hopfield networks to process temporal data and achieve a nonsupervised learning of them. We propose a learning law to address 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 discussed.