ScieNet: Deep learning with s pike-assisted contextual information extraction

[摘要] Spiking neural network (SNN) is a type of artificial neural network that uses biologically inspired neuron models and learning rules to develop artificial intelligence with capability parallel to human brain. Deep neural networks (DNNs), on the other hand, uses less biologically plausible neurons and training meth-ods such as gradient descent, and has shown good accuracy in computer vision tasks. However, human brain can still outperform DNN in certain scenarios. For example, DNN experiences significant perfor-mance degradation when perturbation from various sources is present in the input, which makes DNN less reliable for systems interacting with physical world. In this paper, we present a hybrid deep network architecture with s pike-assisted c ontextual i nformation e xtraction (ScieNet) as a solution to the problem. ScieNet integrates a front-end SNN with a novel stochastic spike-timing-dependent plasticity (STDP) al-gorithm that extracts visual context from images. The back-end DNN is trained for classification given the contextual information. The integrated network demonstrates high resilience to input perturbations without relying on pre-training on perturbed inputs . We demonstrate ScieNet with various back-end DNNs for image classification using different datasets and considering both stochastic and structured input per-turbations. Experimental results demonstrate significant improvement in accuracy on perturbed images, while maintaining state-of-the-art accuracy on clean images. (c) 2021 Elsevier Ltd. All rights reserved.

[发布日期] 2021-10-01

[关键词] Deep learning;Noise robustness;Spiking neural network