无需重训即可跨器件迁移，提升类脑计算效率
Towards transferable lightweight neuromorphic computing through a model-free temporal-switch framework
- 提出无模型时序切换框架，兼容多种硬件设备
- 在未见器件上实现92.4%语音数字识别准确率
- 适用于不同忆阻器类型，适合边缘部署场景
轻量级类脑计算为高效AI提供了可行路径，尤其适合资源受限的边缘部署。然而，由于器件间差异导致性能不稳定，长期依赖重复训练与校准，削弱了实际优势。为此，本文提出无模型时序切换（TS）框架，无需后训练校准即可直接迁移。该框架扩展了训练中可纳入的器件范围，在基于忆阻器的回声状态机验证中，实现了未见过器件上的高性能直接读出。在经典Mackey--Glass预测任务中表现更优，语音数字分类准确率达92.4%。跨不同忆阻器家族与回声状态机配置均验证了其有效性。理论分析揭示其通用计算机制，并表明其可推广至其他物理平台。
原文摘要 · Abstract (English)
Lightweight neuromorphic computing offers a promising route to efficient AI, with particular benefits for resource-constrained edge deployments. However, its scalable deployment that can reliably transfer the expected performance has long been hindered by device-to-device variations, which necessitate costly and repeated re-training on new copies and undermine the practical advantages. To address this issue, we introduce a model-free temporal-switch (TS) framework to improve the direct transfer performance, without post-training calibration or adjustment. The TS framework provides a methodology to incorporate a broader spectrum of devices in the training process. In the validation using memristor-based reservoir computing, it enables high performance on unseen devices with a directly transferred readout. It achieves improved prediction in the representative Mackey--Glass benchmark, and the accuracy of 92.4% in spoken digit classification. Its efficacy is validated across different memristor families and RC configurations. Theoretical analysis not only reveals the general computational mechanism underlying its efficacy, but also underlines its potential applicability to other physical platforms.
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。