Towards transferable lightweight neuromorphic computing through a model-free temporal-switch framework
It addresses device-to-device variation in neuromorphic hardware, a key bottleneck for scalable edge deployment.
The paper introduces a model-free temporal-switch framework to improve direct transfer performance of lightweight neuromorphic computing across devices without retraining, achieving 92.4% accuracy in spoken digit classification and improved prediction on the Mackey-Glass benchmark.
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.