ScieNet: Deep learning with spike-assisted contextual information extraction

作者：

Highlights：

• A new deep learning architecture that integrates spiking neural network (SNN) for contextual information extraction is proposed.

• The proposed design shows improved robustness for both random and structured input perturbation during inference.

• SNN is implemented with a novel frequency-dependent stochastic spike-timing-dependent-plasticity learning rule.

摘要

•A new deep learning architecture that integrates spiking neural network (SNN) for contextual information extraction is proposed.•The proposed design shows improved robustness for both random and structured input perturbation during inference.•SNN is implemented with a novel frequency-dependent stochastic spike-timing-dependent-plasticity learning rule.

论文关键词：Deep learning,Noise robustness,Spiking neural network

论文评审过程：Received 29 October 2019, Revised 20 April 2021, Accepted 24 April 2021, Available online 1 May 2021, Version of Record 26 May 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108002