Online spatio-temporal pattern recognition with evolving spiking neural networks utilising address event representation, rank order, and temporal spike learning

Abstract

Evolving spiking neural networks (eSNN) are computational models that evolve new spiking neurons and new connections from incoming data to learn patterns from them in an on-line mode. With the development of new techniques to capture spatio-and spectro-temporal data in a fast on-line mode, using for example address event representation (AER) such as the implemented one in the artificial retina and the artificial cochlea chips, and with the available SNN hardware technologies, new and more efficient methods for spatio-temporal pattern recognition (STPR) are needed. The paper introduces a new eSNN model dynamic eSNN (deSNN), that utilises both rank-order spike coding (ROSC), also known as time to first spike, and temporal spike coding (TSC). Each of these representations are implemented through different learning mechanisms -RO learning, and temporal spike learning -spike driven synaptic plasticity (SDSP) rule. The deSNN model is demonstrated on a small scale moving object classification problem when AER data is collected with the use of an artificial retina camera. The new model is superior in terms of learning time and accuracy for learning. It makes use of the order of spikes input information which is explicitly present in the AER data, while a temporal spike learning rule accounts for any consecutive spikes arriving on the same synapse that represent temporal components in the learned spatio-temporal pattern. Abstract-Evolving spiking neural networks (eSNN) are computational models that evolve new spiking neurons and new connections from incoming data to learn patterns from them in an on-line mode. With the development of new techniques to capture spatio-and spectro-temporal data in a fast on-line mode, using for example address event representation (AER) such as the implemented one in the artificial retina and the artificial cochlea chips, and with the available SNN hardware technologies, new and more efficient methods for spatio-temporal pattern recognition (STPR) are needed. The paper introduces a new eSNN model dynamic eSNN (deSNN), that utilises both rankorder spike coding (ROSC), also known as time to first spike, and temporal spike coding (TSC). Each of these representations are implemented through different learning mechanisms -RO learning, and temporal spike learning -spike driven synaptic plasticity (SDSP) rule. The deSNN model is demonstrated on a small scale moving object classification problem when AER data is collected with the use of an artificial retina camera. The new model is superior in terms of learning time and accuracy for learning. It makes use of the order of spikes input information which is explicitly present in the AER data, while a temporal spike learning rule accounts for any consecutive spikes arriving on the same synapse that represent temporal components in the learned spatio-temporal pattern.

Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: Design methodology and selected applications

“…• Dynamic eSNN (deSNN) -an architecture that uses both rank-order and time-based learning methods to account for spatio-temporal learning Dhoble et al (2012); Kasabov et al (2013a);…”

Evolving Spiking Neural Networks and Neurogenetic Systems for Spatio- and Spectro-Temporal Data Modelling and Pattern Recognition

“…Examples of problems involving SSTD are: brain cognitive state evaluation based on spatially distributed EEG electrodes [70,26,51,21,99,100] (fig.1a); fMRI data [102] (fig.1b); moving object recognition from video data [23,60,25] (fig.15); spoken word recognition based on spectro-temporal audio data [93,107]; evaluating risk of disease, e.g. heart attack [20]; evaluating response of a disease to treatment based on clinical and environmental variables, e.g.…”

“…In [25] a method for a combined rank-order and temporal (e.g. SDSP) learning is proposed and tested on benchmark data.…”

“…Fig.14 shows a hypothetical engineering system using some of the above tools (from [47,25]). -Moving object recognition ( fig.…”

Evolving spiking neural networks for spatio-and spectro-temporal pattern recognition

“…Synaptic plasticity is employed by a fast supervised one-pass learning algorithm that is explained as part of this section. Following eSNN architectures used both rank-order and time-based learning methods to account for spatio-temporal data [10].…”