SpiNNaker Spatial Learning Code And Dataset

Davies, Sergio ORCID: https://orcid.org/0000-0001-5330-5527, Gait, Andrew, Di Nuovo, Alessandro and Rowley, Andrew (2024) SpiNNaker Spatial Learning Code And Dataset. [Dataset] (Unpublished)

	README file Available under License Creative Commons Attribution. Download (8kB)
	Full Archive Available under License Creative Commons Attribution. Download (6MB)

Abstract

This folder contains all the software and data used in the preparation of the article by: Davies S., Gait A., Rowley A., and Di Nuovo A. "Supervised Learning of Spatial Features with STDP and Homeostasis Using Spiking Neural Networks on SpiNNaker". The data and code are subject to the CC BY license, which can be found in the LICENSE.txt file within the same folder. If this software or data is used in derived publications, a citation to the mentioned article is appreciated by the authors. Artificial Neural Networks (ANN) have gained large popularity thanks to their ability to learn using the well-known backpropagation algorithm. On the other hand, Spiking Neural Networks (SNNs), despite having wider abilities than ANNs, have always presented a challenge in the training phase. This paper shows a new method to perform supervised learning on SNNs, using Spike Timing Dependent Plasticity (STDP) and homeostasis, aiming at training the network to identify spatial patterns. Spatial patterns refer to spike patterns that lack a time component, wherein all spike events occur simultaneously. The method is tested using the SpiNNaker digital architecture. A SNN is trained to recognise one or multiple patterns and performance metrics are extracted to measure the performance of the network. Some considerations are drawn from the results showing that, in the case of a single trained pattern, the network behaves as the ideal detector, with 100% accuracy in detecting the trained pattern. However, as the number of trained patterns on a single network increases, the accuracy of the identification is linked to the similarities between these patterns. This method of training an SNN to detect spatial patterns may be applied on pattern recognition in static images or traffic analysis in computer networks, where each network packet represents a spatial pattern. It will be stipulated that the homeostatic factor may enable the network to detect patterns with some degree of similarities, rather than only perfectly matching patterns. The principles outlined in this article serve as the fundamental building blocks for more complex systems that utilise both spatial and temporal patterns by converting specific features of input signals into spikes. One example of such systems is a computer network packet classifier, tasked with real-time identification of packet streams based on features within the packet content.