An extended Evolving Spiking Neural Network model for spatio-temporal pattern classification

Abstract

This paper proposes a new model of an Evolving Spiking Neural Network (ESNN) for spatio-temporal data (STD) classification problems. The proposed ESNN model incorporates an additional layer for capturing both spatial and temporal components of the STD and then transforms them into high dimensional spiking patterns. These patterns are learned and classified in the evolving classification layer of the ESNN. A fast time-to-first-spike learning algorithm is used that enables the new model to be more suitable for learning from the STD streams in an adaptive and incremental manner. The proposed method is evaluated on a benchmark sign language video that is spatio-temporal in nature. The results show that the proposed method is able to capture important spatio-temporal information from the STD stream. This results in significantly higher classification accuracy than the traditional time-delay MLP neural network model. Future directions for the development of ESNN models for STD are discussed.

Spatio-temporal Pattern Classification with KernelCanvas and WiSARD

“…A larger and more complete description of ESN, including leaking neurons, can be found in [4]. 1 Available at: http://organic.elis.ugent.be/organic/engine …”

“…In fact, according to [1], most of the data we deal today is STD in nature. This kind of data, is frequently generated from the observation of some kind of signal for an amount of time and is usually represented by a matrix of dimension NXM.…”