Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons
Bojković, Velibor Wu, Xiaofeng Gu, Bin
Bojković, Velibor
Wu, Xiaofeng
Gu, Bin
Author
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a promising approach to mitigate the increasing energy demands of large-scale neural models. However, fully harnessing the capabilities of SNNs remains challenging due to their discrete signal processing and temporal dynamics. ANN-SNN conversion has emerged as a practical approach, enabling SNNs to achieve competitive performance on complex machine learning tasks. In this work, we identify a phenomenon in the ANN-SNN conversion framework, termed temporal misalignment, in which random spike rearrangement across SNN layers leads to performance improvements. Based on this observation, we introduce biologically plausible two-phase probabilistic (TPP) spiking neurons, further enhancing the conversion process. We demonstrate the advantages of our proposed method both theoretically and empirically through comprehensive experiments on CIFAR-10/100, CIFAR10-DVS, and ImageNet across a variety of architectures, achieving state-of-the-art results. Codes are available at https://github. com/shizukanaskytree/TPP-SNN.
Citation
V. Bojkovic, X. Wu, and B. Gu, “Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons,” Oct. 06, 2025, PMLR. [Online]. Available: https://proceedings.mlr.press/v267/bojkovic25a.html
Source
Proceedings of Machine Learning Research
Conference
42nd International Conference on Machine Learning, ICML 2025
Keywords
Subjects
Source
42nd International Conference on Machine Learning, ICML 2025
Publisher
ML Research Press