02/02/2021

Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance

Shibo Zhou, Xiaohua Li, Ying Chen, Sanjeev T. Chandrasekaran, Arindam Sanyal

Keywords:

Abstract Paper Similar Papers

Abstract: Spiking neural network (SNN) is promising but the development has fallen far behind conventional deep neural networks (DNNs) because of difficult training. To resolve the training problem, we analyze the closed-form input-output response of spiking neurons and use the response expression to build abstract SNN models for training. This avoids calculating membrane potential during training and makes the direct training of SNN as efficient as DNN. We show that the nonleaky integrate-and-fire neuron with single-spike temporal-coding is the best choice for direct-train deep SNNs. We develop an energy-efficient phase-domain signal processing circuit for the neuron and propose a direct-train deep SNN framework. Thanks to easy training, we train deep SNNs under weight quantizations to study their robustness over low-cost neuromorphic hardware. Experiments show that our direct-train deep SNNs have the highest CIFAR-10 classification accuracy among SNNs, achieve ImageNet classification accuracy within 1% of the DNN of equivalent architecture, and are robust to weight quantization and noise perturbation.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949226
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 0:51 
 0
 1
 0
 1
 3:19 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 4:36 
 0
 0
 0
 0
 13:22 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:13 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 4:06 
 1
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 14:30 
 0
 0
 0
 0
 13:59 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 15:32 
 0
 0
 0
 0
 2:30 
 0
 0
 0
 0
 14:04 
 0
 0
 0
 0
 6:19 
 0
 0
 0
 0
 12:31 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 11:22 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 4:53 
 0
 0
 0
 0
 9:29 
 0
 0
 0
 0
 14:22 
 0
 0
 0
 0
 14:49 
 0
 0
 0
 1
 9:08 
 0
 0
 0
 0
 18:26 
 0
 0
 0
 0
 13:59 
 0
 0
 0
 0
 13:51 
 0
 0
 0
 0
 3:14 
 0
 0
 0
 0
 16:34 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 5:42