A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network from Convolutional Neural Network

Abstract

Spiking neural networks (SNNs) offer an inherent ability to process spatial-temporal data, or in other words, realworld sensory data, but suffer from the difficulty of training high accuracy models. A major thread of research on SNNs is on converting a pre-trained convolutional neural network (CNN) to an SNN of the same structure. State-of-the-art conversion methods are approaching the accuracy limit, i.e., the near-zero accuracy loss of SNN against the original CNN. However, we note that this is made possible only when significantly more energy is consumed to process an input. In this paper, we argue that this trend of "energy for accuracy" is not necessary -- a little energy can go a long way to achieve the near-zero accuracy loss. Specifically, we propose a novel CNN-to-SNN conversion method that is able to use a reasonably short spike train (e.g., 256 timesteps for CIFAR10 images) to achieve the near-zero accuracy loss. The new conversion method, named as explicit current control (ECC), contains three techniques (current normalisation, thresholding for residual elimination, and consistency maintenance for batch-normalisation), in order to explicitly control the currents flowing through the SNN when processing inputs. We implement ECC into a tool nicknamed SpKeras, which can conveniently import Keras CNN models and convert them into SNNs. We conduct an extensive set of experiments with the tool -- working with VGG16 and various datasets such as CIFAR10 and CIFAR100 -- and compare with state-of-the-art conversion methods. Results show that ECC is a promising method that can optimise over energy consumption and accuracy loss simultaneously.

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Exploring the Connection Between Binary and Spiking Neural Networks
• Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks
• RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network

Cited by in corpus (3)

• Beyond spiking networks: the computational advantages of dendritic amplification and input segregation
• Neuromorphic Wireless Split Computing with Multi-Level Spikes
• Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff