Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
作者：
Highlights：
• We used a bio-inspired deep convolutional spiking neural network with latency-coding.
• We trained the low (resp. top) layers with STDP (resp. reward-modulated STDP).
• Accuracy was 97.2% on MNIST, without requiring an external classifier.
• Reward-modulated STDP favors diagnostic features, while STDP favors frequent ones.
• The proposed neuron-based decision-making layer is suitable for energy-efficient hardware implementation.
摘要
•We used a bio-inspired deep convolutional spiking neural network with latency-coding.•We trained the low (resp. top) layers with STDP (resp. reward-modulated STDP).•Accuracy was 97.2% on MNIST, without requiring an external classifier.•Reward-modulated STDP favors diagnostic features, while STDP favors frequent ones.•The proposed neuron-based decision-making layer is suitable for energy-efficient hardware implementation.
论文关键词：Spiking neural networks,Deep architecture,Digit recognition,STDP,Reward-modulated STDP,Latency coding
论文评审过程：Received 31 March 2018, Revised 27 April 2019, Accepted 7 May 2019, Available online 21 May 2019, Version of Record 23 May 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.05.015
