Embracing Stochasticity to Enable Neuromorphic Computing at the Edge

摘要: The advancements of the Internet Things (IoT) and Artificial Intelligence (AI) have resulted in proliferation intelligent computing devices. However, AI-based solutions are often compute-intensive, severely limiting performance edge devices operating energy-constrained environments. As CMOS scaling trends continue to saturate, several emerging technologies shown promise efficient computation. In this paper, we present an overview that exhibit inherent stochasticity how they form building blocks a stochastic framework can execute energy memory-efficient algorithms for computing.