A Memristors-Based Dendritic Neuron for High-Efficiency Spatial-Temporal Information Processing,Advanced Materials

当前位置： X-MOL 学术 › Adv. Mater. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

A Memristors-Based Dendritic Neuron for High-Efficiency Spatial-Temporal Information Processing
Advanced Materials ( IF 27.4 ) Pub Date : 2022-06-23 , DOI: 10.1002/adma.202203684
Xinyi Li _{1,

2} , Yanan Zhong ₃ , Hang Chen ₄ , Jianshi Tang _{1,

2} , Xiaojian Zheng _{1,

2} , Wen Sun _{1,

2} , Yang Li ₅ , Dong Wu _{1,

2} , Bin Gao _{1,

2} , Xiaolin Hu ₄ , He Qian _{1,

2} , Huaqiang Wu _{1,

2}

Affiliation

Diverse microscopic ionic dynamics help mediate the ability of a biological neural network to handle complex tasks with low energy consumption. Thus, rich internal ionic dynamics in memristors based on transition metal oxide are expected to provide a unique and useful platform for implementing energy-efficient neuromorphic computing. To this end, a titanium oxide (TiO_x)-based interface-type dynamic memristor and an niobium oxide (NbO_x)-based Mott memristor are integrated as an artificial dendrite and spike-firing soma, respectively, to construct a dendritic neuron unit for realizing high-efficiency spatial-temporal information processing. Further, a dendritic neural network is hardware-implemented for spatial-temporal information processing to highlight the computational advantages achieved by incorporating dendritic functions in the network. Human motion recognition is demonstrated using the Nanyang Technological University-Red Green Blue (NTU-RGB) dataset as a benchmark spatial-temporal task; it shows a nearly 20% improvement in accuracy for the memristors-based hardware incorporating dendrites and a 1000× advantage in power efficiency compared to that of the graphics processing unit (GPU). The dendritic neuron developed in this study can be considered a critical building block for implementing more bio-plausible neural networks that can manage complex spatial-temporal tasks with high efficiency.

中文翻译：

用于高效时空信息处理的基于忆阻器的树突神经元

不同的微观离子动力学有助于调节生物神经网络以低能耗处理复杂任务的能力。因此，基于过渡金属氧化物的忆阻器中丰富的内部离子动力学有望为实现节能神经形态计算提供独特且有用的平台。为此，将基于氧化钛（TiO _x）的界面型动态忆阻器和基于氧化铌（NbO _x）的莫特忆阻器分别集成为人工树突和尖峰放电体，构建树突神经元单元实现高效的时空信息处理。此外，树突神经网络是硬件实现的，用于时空信息处理，以突出通过在网络中合并树突函数所实现的计算优势。使用南洋理工大学红绿蓝（NTU-RGB）数据集作为基准时空任务演示人体运动识别；与图形处理单元 (GPU) 相比，基于忆阻器的包含树突的硬件的精度提高了近 20%，并且能效比图形处理单元 (GPU) 提高了 1000 倍。本研究中开发的树突神经元可以被认为是实现更符合生物合理性的神经网络的关键构建块，该神经网络可以高效地管理复杂的时空任务。

更新日期：2022-06-23

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11