发表机构
State Key Laboratory of Integrated Chips and Systems; Research Institute of Intelligent Complex Systems; Frontier Institute of Chip and System; School of Mathematical Sciences and Shanghai Center for Mathematical Sciences; Shanghai Artificial Intelligence Laboratory; State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science, Institute of Brain Science（集成芯片与系统国家重点实验室; 智能复杂系统研究院; 芯片与系统前沿院; 数学科学学院和上海数学中心; 上海人工智能实验室; 医学神经生物学国家重点实验室和教育部脑科学前沿中心，脑科学研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对轻量级神经形态计算因设备差异难可靠转移性能问题，引入无模型时间切换框架，无需训练后校准调整，在训练中纳入更多设备，验证其在多种场景高性能及跨不同忆阻器家族和配置的有效性。
AI 中文摘要
轻量级神经形态计算为高效人工智能提供了一条有前景的途径，尤其有利于资源受限的边缘部署。然而，其可扩展部署长期以来一直受到设备间差异的阻碍，这需要在新设备上进行昂贵且重复的重新训练，并削弱了实际优势。为了解决这个问题，我们引入了一个无模型时间切换（TS）框架，以提高直接转移性能，而无需训练后校准或调整。TS框架提供了一种方法，将更广泛的设备纳入训练过程。在基于忆阻器的储层计算的验证中，它通过直接转移的读出在未见设备上实现了高性能。它在代表性的Mackey-Glass基准测试中实现了改进的预测，并在语音数字分类中达到了92.4%的准确率。其有效性在不同的忆阻器家族和RC配置中得到了验证。理论分析不仅揭示了其有效性背后的一般计算机制，还强调了其对其他物理平台的潜在适用性。
英文摘要
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.
