NatCSNN: A Convolutional Spiking Neural Network for recognition of objects extracted from natural images
This work addresses object recognition for computer vision applications, but it is incremental as it builds on existing spiking neural network methods with a specific architecture and training approach.
The paper tackled object recognition from natural images by proposing NatCSNN, a bio-inspired convolutional spiking neural network, achieving an average testing accuracy of 84.7% on CIFAR-10, which improves over prior 2-layer networks.
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.