Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916448543178752 |
|---|---|
| author | Yu, Chengting Liu, Lei Wang, Gaoang Li, Erping Wang, Aili |
| author_facet | Yu, Chengting Liu, Lei Wang, Gaoang Li, Erping Wang, Aili |
| contents | Recent insights have revealed that rate-coding is a primary form of information representation captured by surrogate-gradient-based Backpropagation Through Time (BPTT) in training deep Spiking Neural Networks (SNNs). Motivated by these findings, we propose rate-based backpropagation, a training strategy specifically designed to exploit rate-based representations to reduce the complexity of BPTT. Our method minimizes reliance on detailed temporal derivatives by focusing on averaged dynamics, streamlining the computational graph to reduce memory and computational demands of SNNs training. We substantiate the rationality of the gradient approximation between BPTT and the proposed method through both theoretical analysis and empirical observations. Comprehensive experiments on CIFAR-10, CIFAR-100, ImageNet, and CIFAR10-DVS validate that our method achieves comparable performance to BPTT counterparts, and surpasses state-of-the-art efficient training techniques. By leveraging the inherent benefits of rate-coding, this work sets the stage for more scalable and efficient SNNs training within resource-constrained environments. Our code is available at https://github.com/Tab-ct/rate-based-backpropagation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11488 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation Yu, Chengting Liu, Lei Wang, Gaoang Li, Erping Wang, Aili Machine Learning Neural and Evolutionary Computing Recent insights have revealed that rate-coding is a primary form of information representation captured by surrogate-gradient-based Backpropagation Through Time (BPTT) in training deep Spiking Neural Networks (SNNs). Motivated by these findings, we propose rate-based backpropagation, a training strategy specifically designed to exploit rate-based representations to reduce the complexity of BPTT. Our method minimizes reliance on detailed temporal derivatives by focusing on averaged dynamics, streamlining the computational graph to reduce memory and computational demands of SNNs training. We substantiate the rationality of the gradient approximation between BPTT and the proposed method through both theoretical analysis and empirical observations. Comprehensive experiments on CIFAR-10, CIFAR-100, ImageNet, and CIFAR10-DVS validate that our method achieves comparable performance to BPTT counterparts, and surpasses state-of-the-art efficient training techniques. By leveraging the inherent benefits of rate-coding, this work sets the stage for more scalable and efficient SNNs training within resource-constrained environments. Our code is available at https://github.com/Tab-ct/rate-based-backpropagation. |
| title | Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation |
| topic | Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2410.11488 |