Core processing neuron‐enabled circuit motifs for neuromorphic computing

AbstractBased on brain‐inspired computing frameworks, neuromorphic systems implement large‐scale neural networks in hardware. Although rapid advances have been made in the development of artificial neurons and synapses in recent years, further research is beyond these individual components and focuses on neuronal circuit motifs with specialized excitatory–inhibitory (E–I) connectivity patterns. In this study, we demonstrate a core processor that can be used to construct commonly used neuronal circuits. The neuron, featuring an ultracompact physical configuration, integrates a volatile threshold switch with a gate‐modulated two‐dimensional (2D) MoS2 field‐effect channel to process complex E–I spatiotemporal spiking signals. Consequently, basic neuronal circuits are constructed for biorealistic neuromorphic computing. For practical applications, an algorithm‐hardware co‐design is implemented in a gate‐controlled spiking neural network with substantial performance improvement in human speech separation.image

Editorial: Cutting-edge systems and materials for brain-inspired computing, adaptive bio-interfacing and smart sensing: implications for neuromorphic computing and biointegrated frameworks

2D Ferroionics: Conductive Switching Mechanisms and Transition Boundaries in Van der Waals Layered Material CuInP₂S₆ (Adv. Mater. 38/2023)

2D Ferroionics: Conductive Switching Mechanisms and Transition Boundaries in Van der Waals Layered Material CuInP₂S₆

AbstractThe recently unfolded ferroionic phenomena in 2D van der Waals (vdW) copper–indium–thiophosphate (CuInP2S6 or CIPS) have received widespread interest as they allow for dynamic control of conductive switching properties, which are appealing in the paradigm‐shift computing. The intricate couplings between ferroelectric polarization and ionic conduction in 2D vdW CIPS facilitate the manipulation and dynamic control of conductive behaviors. However, the complex interplays and underlying mechanisms are not yet fully explored and understood. Here, by investigating polarization switching and ionic conduction in the temperature and applied electric field domains, it is discovered that the conducting mechanisms of CIPS can be divided into four distinctive states (or modes) with transitional boundaries, depending on the dynamics of Cu ions in the material. Further, it demonstrates that dynamically‐tunable synaptic responsive behavior can be well implemented by governing the working‐state transition. This research provides an in‐depth, quantitative understanding of the complex phenomena of conductive switching in 2D vdW CIPS with coexisting ferroelectric order and ionic disorder. The developed insights in this work lay the ground for implementing high‐performance, function‐enriched devices for information processing, data storage, and neuromorphic computing based on the 2D ferroionic material systems.

Foreword to the Special Issue on Deep Learning and Neuromorphic Chips

With the advent of the Internet of Things and the era of big data, the ability of machine data processing to reach the level of human brain cognition and learning is an important goal in the field of Internet information technology, including cloud computing, data mining, machine learning, and artificial intelligence (AI) [...]

Single‐Transistor Neuron with Excitatory–Inhibitory Spatiotemporal Dynamics Applied for Neuronal Oscillations

AbstractBrain‐inspired neuromorphic computing systems with the potential to drive the next wave of artificial intelligence demand a spectrum of critical components beyond simple characteristics. An emerging research trend is to achieve advanced functions with ultracompact neuromorphic devices. In this work, a single‐transistor neuron is demonstrated that implements excitatory–inhibitory (E–I) spatiotemporal integration and a series of essential neuron behaviors. Neuronal oscillations, the fundamental mode of neuronal communication, that construct high‐dimensional population code to achieve efficient computing in the brain, can also be demonstrated by the neuron transistors. The highly scalable E–I neuron can be the basic building block for implementing core neuronal circuit motifs and large‐scale architectural plans to replicate energy‐efficient neural computations, forming the foundation of future integrated neuromorphic systems.