BSNN: Towards Faster and Better Conversion of Artificial Neural Networks to Spiking Neural Networks with Bistable Neurons
This addresses the problem of inefficient ANN-to-SNN conversion for researchers and engineers in neuromorphic computing, offering a novel method to reduce time delays and performance loss, though it is incremental as it builds on existing conversion techniques.
The paper tackles performance loss and time delays in converting artificial neural networks (ANNs) to spiking neural networks (SNNs) by proposing a bistable spiking neural network (BSNN) with synchronous neurons, achieving nearly lossless conversion with only 1/4-1/10 of the time steps and state-of-the-art results on datasets like CIFAR-10 (95.16% top-1), CIFAR-100 (78.12% top-1), and ImageNet (72.64% top-1).
The spiking neural network (SNN) computes and communicates information through discrete binary events. It is considered more biologically plausible and more energy-efficient than artificial neural networks (ANN) in emerging neuromorphic hardware. However, due to the discontinuous and non-differentiable characteristics, training SNN is a relatively challenging task. Recent work has achieved essential progress on an excellent performance by converting ANN to SNN. Due to the difference in information processing, the converted deep SNN usually suffers serious performance loss and large time delay. In this paper, we analyze the reasons for the performance loss and propose a novel bistable spiking neural network (BSNN) that addresses the problem of spikes of inactivated neurons (SIN) caused by the phase lead and phase lag. Also, when ResNet structure-based ANNs are converted, the information of output neurons is incomplete due to the rapid transmission of the shortcut path. We design synchronous neurons (SN) to help efficiently improve performance. Experimental results show that the proposed method only needs 1/4-1/10 of the time steps compared to previous work to achieve nearly lossless conversion. We demonstrate state-of-the-art ANN-SNN conversion for VGG16, ResNet20, and ResNet34 on challenging datasets including CIFAR-10 (95.16% top-1), CIFAR-100 (78.12% top-1), and ImageNet (72.64% top-1).