The ability of high‐order tuning of the synaptic plasticity in an artificial synapse can offer significant improvement in the processing time, low‐power recognition, and learning capability in a neuro‐inspired computing system. Inspired by light‐assisted dopamine‐facilitated synaptic activity, which achieves rapid learning and adaptation by lowering the threshold of the synaptic plasticity, a two‐terminal organolead halide perovskite (OHP)‐based photonic synapse is fabricated and designed in which the synaptic plasticity is modified by both electrical pulses and light illumination. Owing to the accelerated migration of the iodine vacancy inherently existing in the coated OHP film under light illumination, the OHP synaptic device exhibits light‐tunable synaptic functionalities with very low programming inputs (≈0.1 V). It is also demonstrated that the threshold of the long‐term potentiation decreases and synaptic weight further modulates when light illuminates the device, which is phenomenologically analogous to the dopamine‐assisted synaptic process. Notably, under light exposure, the OHP synaptic device achieves rapid pattern recognition with ≈81.8% accuracy after only 2000 learning phases (60 000 learning phases = one epoch) with a low‐power consumption (4.82 nW/the initial update for potentiation), which is ≈2.6 × 103 times lower than when the synaptic weights are updated by only high electrical pulses.

No abstract

No abstract

Modern artificial neural network technology using a deterministic computing framework is faced with a critical challenge in dealing with massive data that are largely unstructured and ambiguous. This challenge demands the advances of an elementary physical device for tackling these uncertainties. Here, we designed and fabricated a SiOx nanorod memristive device by employing the glancing angle deposition (GLAD) technique, suggesting a controllable stochastic artificial neuron that can mimic the fundamental integrate‐and‐fire signaling and stochastic dynamics of a biological neuron. The nanorod structure provides the random distribution of multiple nanopores all across the active area, capable of forming a multitude of Si filaments at many SiOx nanorod edges after the electromigration process, leading to a stochastic switching event with very high dynamic range (≈5.15 × 1010) and low energy (≈4.06 pJ). Different probabilistic activation (ProbAct) functions in a sigmoid form are implemented, showing its controllability with low variation by manufacturing and electrical programming schemes. Furthermore, as an application prospect, based on the suggested memristive neuron, we demonstrated the self‐resting neural operation with the local circuit configuration and revealed probabilistic Bayesian inferences for genetic regulatory networks with low normalized mean squared errors (≈2.41 × 10‐2) and its robustness to the ProbAct variation.

No abstract