Hardware in Loop Learning with Spin Stochastic Neurons

2023/05/05 by A N M Nafiul Islam, Kezhou Yang, Islam, A N M Nafiul +11
Computer Science · Engineering · #Advanced Memory and Neural Computing #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Neural Networks and Reservoir Computing

paper · pdf · doi:10.48550/arxiv.2305.03235

openalex publication_date 2023/05/05 · openalex created_date 2023/05/18 · openalex updated_date 2026/07/28

Abstract

Despite the promise of superior efficiency and scalability, real-world deployment of emerging nanoelectronic platforms for brain-inspired computing have been limited thus far, primarily because of inter-device variations and intrinsic non-idealities. In this work, we demonstrate mitigating these issues by performing learning directly on practical devices through a hardware-in-loop approach, utilizing stochastic neurons based on heavy metal/ferromagnetic spin-orbit torque heterostructures. We characterize the probabilistic switching and device-to-device variability of our fabricated devices of various sizes to showcase the effect of device dimension on the neuronal dynamics and its consequent impact on network-level performance. The efficacy of the hardware-in-loop scheme is illustrated in a deep learning scenario achieving equivalent software performance. This work paves the way for future large-scale implementations of neuromorphic hardware and realization of truly autonomous edge-intelligent devices.

Related

• Stochastic Spin-Orbit Torque Devices as Elements for Bayesian Inference
• Electrically-Tunable Stochasticity for Spin-based Neuromorphic Circuits:\n Self-Adjusting to Variation
• Machine learning using magnetic stochastic synapses
• A novel compound synapse using probabilistic spin-orbit-torque switching\n for MTJ based deep neural networks
• Uncontrolled learning: co-design of neuromorphic hardware topology for neuromorphic algorithms