In-Memory Mathematical Operations with Spin-Orbit Torque Devices

Restricted Boltzmann Machines Implemented by Spin-Orbit Torque Magnetic Tunnel Junctions

Artificial intelligence has surged forward with the advent of generative models, which rely heavily on stochastic computing architectures enhanced by true random number generators with adjustable sampling probabilities. In this study, we develop spin-orbit torque magnetic tunnel junctions (SOT-MTJs), investigating their sigmoid-style switching probability as a function of the driving voltage. This feature proves to be ideally suited for stochastic computing algorithms such as the restricted Boltzmann machines (RBM) prevalent in pretraining processes. We exploit SOT-MTJs as both stochastic samplers and network nodes for RBMs, enabling the implementation of RBM-based neural networks to achieve recognition tasks for both handwritten and spoken digits. Moreover, we further harness the weights derived from the preceding image and speech training processes to facilitate cross-modal learning from speech to image generation. Our results clearly demonstrate that these SOT-MTJs are promising candidates for the development of hardware accelerators tailored for Boltzmann neural networks and other stochastic computing architectures.

Memristor-Based Artificial Chips

Memristors, promising nanoelectronic devices with in-memory resistive switching behavior that is assembled with a physically integrated core processing unit (CPU) and memory unit and even possesses highly possible multistate electrical behavior, could avoid the von Neumann bottleneck of traditional computing devices and show a highly efficient ability of parallel computation and high information storage. These advantages position them as potential candidates for future data-centric computing requirements and add remarkable vigor to the research of next-generation artificial intelligence (AI) systems, particularly those that involve brain-like intelligence applications. This work provides an overview of the evolution of memristor-based devices, from their initial use in creating artificial synapses and neural networks to their application in developing advanced AI systems and brain-like chips. It offers a broad perspective of the key device primitives enabling their special applications from the view of materials, nanostructure, and mechanism models. We highlight these demonstrations of memristor-based nanoelectronic devices that have potential for use in the field of brain-like AI, point out the existing challenges of memristor-based nanodevices toward brain-like chips, and propose the guiding principle and promising outlook for future device promotion and system optimization in the biomedical AI field.