A New ANN-SNN Conversion Method with High Accuracy, Low Latency and Good Robustness
A New ANN-SNN Conversion Method with High Accuracy, Low Latency and Good Robustness
Bingsen Wang, Jian Cao, Jue Chen, Shuo Feng, Yuan Wang
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence
Main Track. Pages 3067-3075.
https://doi.org/10.24963/ijcai.2023/342
Due to the advantages of low energy consumption, high robustness and fast inference speed, Spiking Neural Networks (SNNs), with good biological interpretability and the potential to be applied on neuromorphic hardware, are regarded as the third generation of Artificial Neural Networks (ANNs). Despite having so many advantages, the biggest challenge encountered by spiking neural networks is training difficulty caused by the non-differentiability of spike signals. ANN-SNN conversion is an effective method that solves the training difficulty by converting parameters in ANNs to those in SNNs through a specific algorithm. However, the ANN-SNN conversion method also suffers from accuracy degradation and long inference time. In this paper, we reanalyzed the relationship between Integrate-and-Fire (IF) neuron model and ReLU activation function, proposed a StepReLU activation function more suitable for SNNs under membrane potential encoding, and used it to train ANNs. Then we converted the ANNs to SNNs with extremely small conversion error and introduced leakage mechanism to the SNNs and get the final models, which have high accuracy, low latency and good robustness, and have achieved the state-of-the-art performance on various datasets such as CIFAR and ImageNet.
Keywords:
Humans and AI: HAI: Cognitive modeling
Machine Learning: ML: Classification
Computer Vision: CV: Machine learning for vision
Machine Learning: ML: Robustness