Deep Spiking Neural Network with Spike Count based Learning Rule

Deep Spiking Neural Network with Spike Count based Learning Rule
Title:
Deep Spiking Neural Network with Spike Count based Learning Rule
Other Titles:
The International Joint Conference on Neural Networks (IJCNN)
Publication URL:
Keywords:
Publication Date:
15 February 2019
Citation:
Abstract:
Deep spiking neural networks (SNNs) support asynchronous event-driven computation, massive parallelism and demonstrate great potential to improve the energy efficiency of its synchronous analog counterpart. However, insufficient attention has been paid to neural encoding when designing SNN learning rules. Remarkably, the temporal credit assignment has been performed on rate-coded spiking inputs, leading to poor learning efficiency. In this paper, we introduce a novel spike-based learning rule for rate-coded deep SNNs, whereby the spike count of each neuron is used as a surrogate for gradient backpropagation. We evaluate the proposed learning rule by training deep spiking multi-layer perceptron (MLP) and spiking convolutional neural network (CNN) on the UCI machine learning and MNIST handwritten digit datasets. We show that the proposed learning rule achieves state-of-the-art accuracies on all benchmark datasets. The proposed learning rule allows introducing latency, spike rate and hardware constraints into the SNN learning, which is superior to the indirect approach in which conventional artificial neural networks are first trained and then converted to SNNs. Hence, it allows direct deployment to the neuromorphic hardware and supports efficient inference. Notably, a test accuracy of 98.40% was achieved on the MNIST dataset in our experiments with only 10 simulation time steps, when the same latency constraint is imposed during training.
License type:
Funding Info:
This research is supported by Programmatic grant no. A1687b0033 from the Singapore governments Research, Innovation and Enterprise 2020 plan (Advanced Manufacturing and Engineering domain).
Description:
ISBN:

Files uploaded:
File Size Format Action
There are no attached files.