Skin-like n-type stretchable synaptic transistors with low energy consumption and highly reliable plasticity for brain-inspired computing

Abstract

Artificial synaptic devices with high transconductance, low energy consumption and good stretchability are important for efficient and energy-friendly neuromorphic computations in the field of bionics. Here, we propose a stretchable substrate inspired by wrinkled surface of human skin, and achieve a low energy operation stretchable synaptic transistor (SST) based on n-type oxide semiconductor. The SSTs exhibit excellent performance, including high mobility (4.08 cm2V−1s−1) and high transconductance (over 12 mS) under ultra-low operation voltage of 0.1 V. They can stand against multi-directional stretching of 10 % and up to 400 stretch/release cycles. In addition, the n-type SSTs achieve synaptic performance at ultra-low energy consumption (0.36 fJ) with dual-mode operation characteristics of excitatory and inhibitory behaviors. Under tensile strain, they exhibit typical synaptic behavior, including short-term/long-term plasticity, pair pulse facilitation, spike voltage/frequency/duration/number-dependent plasticity. More importantly, the SSTs exhibit excellent “learning-forgetting-relearning” feature and good stability under potentiation-depression cycle test, showcasing tremendous potential in brain-inspired computation. Finally, a high recognition accuracy (89.6 %) is attained simulated by handwritten digital datasets. To the best of our knowledge, this is the first stretchable synaptic transistor with oxide semiconductors, and it is also a major breakthrough in n-type stretchable synaptic transistors for high-speed and low-energy calculation and storage for brain-inspired computing.