Premium
Photonic Organolead Halide Perovskite Artificial Synapse Capable of Accelerated Learning at Low Power Inspired by Dopamine‐Facilitated Synaptic Activity
Author(s) -
Ham Seonggil,
Choi Sanghyeon,
Cho Haein,
Na SeokIn,
Wang Gunuk
Publication year - 2019
Publication title -
advanced functional materials
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.069
H-Index - 322
eISSN - 1616-3028
pISSN - 1616-301X
DOI - 10.1002/adfm.201806646
Subject(s) - synaptic plasticity , long term potentiation , materials science , synapse , synaptic weight , perovskite (structure) , synaptic augmentation , dopamine , neuroscience , optoelectronics , computer science , artificial neural network , artificial intelligence , chemistry , biology , biochemistry , receptor , crystallography
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 × 10 3 times lower than when the synaptic weights are updated by only high electrical pulses.