Litcius/Paper detail

Analog memristive synapse based on topotactic phase transition for high-performance neuromorphic computing and neural network pruning

Xing Mou, Jianshi Tang, Yingjie Lyu, Qingtian Zhang, Siyao Yang, Feng Xu, Wei Liu, Minghong Xu, Yu Zhou, Wen Sun, Ya‐Nan Zhong, Bin Gao, Pu Yu, He Qian, Huaqiang Wu

2021Science Advances121 citationsDOIOpen Access PDF

Abstract

is well controlled by oxygen ion migrations along the highly ordered oxygen vacancy channels, enabling reproducible analog switching characteristics with reduced variability. Combining density functional theory and kinetic Monte Carlo simulations, the orientation-dependent switching mechanism of TPT-RAM is investigated synergistically. Furthermore, the dual-mode TPT-RAM is used to mimic the selective stabilization of developing synapses and implement neural network pruning, reducing ~84.2% of redundant synapses while improving the image classification accuracy to 99%. Our work points out a new direction to design bioplausible memristive synapses for neuromorphic computing.

Topics & Concepts

Neuromorphic engineeringPruningMemristorArtificial neural networkSynapseComputer sciencePhase transitionMaterials scienceNeuroscienceArtificial intelligencePhysicsElectronic engineeringEngineeringBiologyAgronomyQuantum mechanicsAdvanced Memory and Neural ComputingPhotoreceptor and optogenetics researchNeural dynamics and brain function