用强化学习精准压缩脉冲神经网络，确保计算量达标。
SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning
- 通过预测机制LRE预估剪枝后突触操作数，实现动态约束。
- 设计新奖励函数TAR，使搜索过程稳定在目标突触操作数内。
- 适合需严格控制计算量的神经形态硬件部署场景。
深度脉冲神经网络（SNN）虽性能优越，但在资源受限的类脑硬件上部署仍具挑战。网络剪枝可通过减少参数和突触操作（SynOps）来促进SNN的边缘部署，其中基于搜索的剪枝方法在剪枝后搜索最优结构。然而，现有方法无法直接以SynOps为约束，因其在搜索过程中动态变化，导致最终网络偏离预期的SynOps目标。本文提出一种新型SNN剪枝框架SPEAR，利用强化学习（RL）技术直接将SynOps作为搜索约束。为避免违反约束，我们首先提出一种名为LRE的突触操作预测机制，可准确预测剪枝后的最终SynOps。由于SynOps无法显式计算并用于约束动作空间，我们设计了一种新型奖励函数TAR，以稳定搜索过程。大量实验表明，SPEAR框架可在特定SynOps约束下有效压缩SNN。
原文摘要 · Abstract (English)
While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable solution by reducing both parameters and synaptic operations (SynOps) to facilitate the edge deployment of SNNs, among which search-based pruning methods search for the SNNs structure after pruning. However, existing search-based methods fail to directly use SynOps as the constraint because it will dynamically change in the searching process, resulting in the final searched network violating the expected SynOps target. In this paper, we introduce a novel SNN pruning framework called SPEAR, which leverages reinforcement learning (RL) technique to directly use SynOps as the searching constraint. To avoid the violation of SynOps requirements, we first propose a SynOps prediction mechanism called LRE to accurately predict the final SynOps after search. Observing SynOps cannot be explicitly calculated and added to constrain the action in RL, we propose a novel reward called TAR to stabilize the searching. Extensive experiments show that our SPEAR framework can effectively compress SNN under specific SynOps constraint.
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。