NatCSNN: a convolutional spiking neural network for recognition of objects extracted from natural images

Tools

Machado, P ORCID: https://orcid.org/0000-0003-1760-3871 and Cosma, G ORCID: https://orcid.org/0000-0002-4663-6907, 2019. NatCSNN: a convolutional spiking neural network for recognition of objects extracted from natural images. In: ICANN 2019: 28th International Conference on Artificial Neural Networks, Munich, Germany, 17–19 September 2019. (Forthcoming)

Preview

Text
14013_Machado.pdf - Pre-print
Download (357kB) | Preview

Abstract

Biological image processing is performed by complex neural networks composed of thousands of neurons interconnected via thousands of synapses, some of which are excitatory and others inhibitory. Spiking neural models are distinguished from classical neurons by being biological plausible and exhibiting the same dynamics as those observed in biological neurons. This paper proposes a Natural Convolutional Neural Network (NatCSNN) which is a 3-layer bio-inspired Convolutional Spiking Neural Network (CSNN), for classifying objects extracted from natural images. A two-stage training algorithm is proposed using unsupervised Spike Timing Dependent Plasticity (STDP) learning (phase 1) and ReSuMe supervised learning (phase 2). The NatCSNN was trained and tested on the CIFAR-10 dataset and achieved an average testing accuracy of 84.7% which is an improvement over the 2-layer neural networks previously applied to this dataset

Item Type:	Conference contribution
Creators:	Machado, P. and Cosma, G.
Date:	September 2019
Divisions:	Schools > School of Science and Technology
Record created by:	Linda Sullivan
Date Added:	11 Jun 2019 08:47
Last Modified:	30 Sep 2019 03:00
Related URLs:	Organisation
URI:	https://irep.ntu.ac.uk/id/eprint/36729