Geoffrey W. Burr; R. M. Shelby; Abu Sebastian; Sang‐Bum Kim; Seyoung Kim; Severin Sidler; Kumar Virwani; Masatoshi Ishii; Pritish Narayanan; Alessandro Fumarola; Lucas L. Sanches; Irem Boybat; Manuel Le Gallo; Kibong Moon; Jiyoo Woo; Hyunsang Hwang; Yusuf Leblebici · 2016 · Advances in Physics X
Paper
Dense crossbar arrays of non-volatile memory (NVM) devices represent one possible path for implementing massively-parallel and highly energy-efficient neuromorphic computing systems. We first review recent advances in the application of NVM devices to three computing paradigms: spiking neural networks (SNNs), deep neural networks (DNNs), and âMemcomputingâ. In SNNs, NVM synaptic connections are updated by a local learning rule such as spike-timing-dependent-plasticity, a computational approach directly inspired by biology. For DNNs, NVM arrays can represent matrices of synaptic weights, implementing the matrixâvector multiplication needed for algorithms such as backpropagation in an analog yetmassively-parallel fashion. This approach could provide significant improvements in power and speed compared to GPU-based DNN training, for applications of commercial significance. We then survey recent research in which different types of NVM devices â including phase change memory, conductive-bridging RAM, filamentary and nonfilamentary RRAM, and other NVMs â have been proposed, either as a synapse or as a neuron, for use within a neuromorphic computing application. The relevant virtues and limitations of these devices are assessed, in terms of properties such as conductance dynamic range, (non)linearity and (a)symmetry of conductance response, retention, endurance, required switching power, and device variability.
Analysis
This paper reviews advances in non-volatile memory (NVM) devices for neuromorphic computing, focusing on their application in spiking neural networks (SNNs), deep neural networks (DNNs), and 'Memcomputing'.
Discovery
Fernando Aguirre; Abu Sebastian; Manuel Le Gallo; Wenhao Song; Tong Wang; J. Joshua Yang; Wei Lü; Meng‐Fan Chang; Daniele Ielmini; Yuchao Yang; Adnan Mehonić; Anthony J. Kenyon; Marco A. Villena; J.B. Roldán; Yuting Wu; Hung-Hsi Hsu; Nagarajan Raghavan; J. Suñé; E. Miranda; Ahmed M. Eltawil; Gianluca Setti; Kamilya Smagulova; K. Saláma; Olga Krestinskaya; Xiaobing Yan; Kah‐Wee Ang; Samarth Jain; Sifan Li; Osamah Alharbi; Sebastián Pazos; Mario Lanza
Dwipak Prasad Sahu; Kitae Park; Peter Hayoung Chung; Jimin Han; Tae‐Sik Yoon
Sundar Kunwar; Zachary Jernigan; Zach Hughes; Chase Somodi; Michael Saccone; Francesco Caravelli; Pinku Roy; Di Zhang; Haiyan Wang; Q. X. Jia; Judith L. MacManus‐Driscoll; Garrett T. Kenyon; Andrew Sornborger; Wanyi Nie; Aiping Chen
Ji Hyun Baek; Kyung Ju Kwak; Seung Ju Kim; Jaehyun Kim; Jae Young Kim; In Hyuk Im; Sunyoung Lee; Kisuk Kang; Ho Won Jang
Xuwen Xia; Wen Huang; Pengjie Hang; Tao Guo; Yong Yan; Jianping Yang; Deren Yang; Xuegong Yu; Xing’ao Li
Matteo Farronato; Piergiulio Mannocci; Margherita Melegari; Saverio Ricci; Christian Monzio Compagnoni; Daniele Ielmini
Source record