Abstract
Spiking Neural Networks (SNNs) have recently emerged as a prominent neural computing paradigm. However, the typical shallow SNN architectures have limited capacity for expressing complex representations while training deep SNNs using input spikes has not been successful so far. Diverse methods have been proposed to get around this issue such as converting off-the-shelf trained deep Artificial Neural Networks (ANNs) to SNNs. However, the ANN-SNN conversion scheme fails to capture the temporal dynamics of a spiking system. On the other hand, it is still a difficult problem to directly train deep SNNs using input spike events due to the discontinuous, non-differentiable nature of the spike generation function. To overcome this problem, we propose an approximate derivative method that accounts for the leaky behavior of LIF neurons. This method enables training deep convolutional SNNs directly (with input spike events) using spike-based backpropagation. Our experiments show the effectiveness of the proposed spike-based learning on deep networks (VGG and Residual architectures) by achieving the best classification accuracies in MNIST, SVHN, and CIFAR-10 datasets compared to other SNNs trained with a spike-based learning. Moreover, we analyze sparse event-based computations to demonstrate the efficacy of the proposed SNN training method for inference operation in the spiking domain.
Highlights
Over the last few years, deep learning has made tremendous progress and has become a prevalent tool for performing various cognitive tasks such as object detection, speech recognition, and reasoning
Benchmarking Datasets We demonstrate the efficacy of our proposed training methodology for deep convolutional Spike-Based LearningSpiking Neural Network (SNN) on three standard vision datasets and one neuromorphic vision dataset, namely the MNIST (LeCun et al, 1998), SVHN (Netzer et al, 2011), CIFAR10 (Krizhevsky and Hinton, 2009), and N-MNIST (Orchard et al, 2015)
We analyze the classification performance and efficiency achieved by the proposed spike-based training methodology for deep convolutional SNNs compared to the performance of the transformed SNN using Artificial Neural Networks (ANNs)-SNN conversion scheme
Summary
Over the last few years, deep learning has made tremendous progress and has become a prevalent tool for performing various cognitive tasks such as object detection, speech recognition, and reasoning. Specialized hardwares (Merolla et al, 2014; Ankit et al, 2017; Davies et al, 2018) have been developed to exploit this eventbased, asynchronous signaling/processing scheme. They are promising for achieving ultra-low power intelligent processing of streaming spatiotemporal data, and especially in deep hierarchical networks, as it has been observed in SNN models that the number of spikes, and the amount of computation, decreases significantly at deeper layers (Rueckauer et al, 2017; Sengupta et al, 2019)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
