Optically driven intelligent computing with ZnO memristor

TLDR

Artificial vision is essential for AI, yet conventional systems suffer real‑time bottlenecks from separate sensors, memories, and processors; optoelectronic memristors that integrate sensing, computing, and memory are promising, but existing devices only support monotonic conductance changes under light. The authors propose an all‑optically controlled Au/ZnO/Pt memristive ISCM device fabricated with ZnO sputtered in pure Ar. The device employs a simple Au/ZnO/Pt stack with ZnO deposited in pure Ar to enable reversible memconductance tuning by light. It achieves light‑only nonvolatile neuromorphic computing and Boolean logic, shows excellent stability from purely electronic tuning, and represents a significant step toward next‑generation artificial visual systems.

Abstract

Artificial vision is crucial for most artificial intelligence applications. Conventional artificial visual systems have been facing challenges in terms of real-time information processing due to the physical separation of sensors, memories, and processors, which results in the production of a large amount of redundant data as well as the data conversion and transfer between these three components consuming most of the time and energy. Emergent optoelectronic memristors with the ability to realize integrated sensing-computing-memory (ISCM) are key candidates for solving such challenges and therefore attract increasing attention. At present, the memristive ISCM devices can only perform primary-level computing with external light signals due to the fact that only monotonic increase of memconductance upon light irradiation is achieved in most of these devices. Here, we propose an all-optically controlled memristive ISCM device based on a simple structure of Au/ZnO/Pt with the ZnO thin film sputtered at pure Ar atmosphere. This device can perform advanced computing tasks such as nonvolatile neuromorphic computing and complete Boolean logic functions only by light irradiation, owing to its ability to reversibly tune the memconductance with light. Moreover, the device shows excellent operation stability ascribed to a purely electronic memconductance tuning mechanism. Hence, this study is an important step towards the next generation of artificial visual systems.