On temporal sequence storage

Presents a theoretical analysis and a series of simulations of a method for temporal sequence storage. The method is based on the power of leaky integrator neurons to store previous inputs over a range of times in the past. The theory and simulations presented here agree for the particular training rule which is of the simplest kind: to train the output so as to look as close as possible like the succeeding input. This is a version of the delta learning rule, which can be implemented in a local manner if there is suitable net architecture.<
>