An extension of an evolving spiking neural network (eSNN) is proposed that enables the method to process spatio-temporal information. In this extension, an additional layer is added to the network architecture that transforms a spatio-temporal input pattern into a single intermediate high-dimensional network state which in turn is mapped into a desired class label using a fast one-pass learning algorithm. The intermediate state is represented by a novel probabilistic reservoir computing approach in which a stochastic neural model introduces a non-deterministic component into a liquid state machine. A proof of concept is presented demonstrating an improved separation capability of the reservoir and consequently its suitability for an eSNN extension.
Stefan Schliebs hasn't uploaded this paper.
Let Stefan know you want this paper to be uploaded.
