提出随机架构脉冲神经网络，仅需训练部分权重即可高效稳定部署。
Spiking Neural Networks with Random Network Architecture
- 采用随机网络结构，仅需训练部分权重
- 兼容经典训练方法，效率显著提升
- 在基准测试中表现稳定，适合实际应用
脉冲神经网络（SNN）作为第三代神经网络，因其符合生物合理性的信息传播机制，在高能场景下具备显著能效优势。然而，由于脉冲发放机制的不连续与不可导性，其模型和训练方法尚未统一。尽管已有多种训练算法被提出，但核心问题仍未解决。受随机网络设计启发，本文提出新架构RanSNN：仅需训练部分网络权重，且可直接采用经典训练方法。相比传统SNN训练方式，该方法大幅提升了训练效率并保持性能，经基准测试验证具有良好的通用性与稳定性。
原文摘要 · Abstract (English)
The spiking neural network, known as the third generation neural network, is an important network paradigm. Due to its mode of information propagation that follows biological rationality, the spiking neural network has strong energy efficiency and has advantages in complex high-energy application scenarios. However, unlike the artificial neural network (ANN) which has a mature and unified framework, the SNN models and training methods have not yet been widely unified due to the discontinuous and non-differentiable property of the firing mechanism. Although several algorithms for training spiking neural networks have been proposed in the subsequent development process, some fundamental issues remain unsolved. Inspired by random network design, this work proposes a new architecture for spiking neural networks, RanSNN, where only part of the network weights need training and all the classic training methods can be adopted. Compared with traditional training methods for spiking neural networks, it greatly improves the training efficiency while ensuring the training performance, and also has good versatility and stability as validated by benchmark tests.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。