NatCSNN: A Convolutional Spiking Neural Network for recognition of objects extracted from natural images

TL;DR

This paper introduces NatCSNN, a biologically inspired 3-layer convolutional spiking neural network that classifies natural images with high accuracy using a novel two-stage training process.

Contribution

It presents a new bio-inspired convolutional spiking neural network with a two-stage training algorithm combining STDP and ReSuMe, achieving improved accuracy on CIFAR-10.

Findings

Achieved 84.7% accuracy on CIFAR-10

Outperformed previous 2-layer neural networks on the same dataset

Demonstrated effectiveness of bio-inspired training methods

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.