DocumentCode :
1764462
Title :
HfO2-Based OxRAM Devices as Synapses for Convolutional Neural Networks
Author :
Garbin, Daniele ; Vianello, Elisa ; Bichler, Olivier ; Rafhay, Quentin ; Gamrat, Christian ; Ghibaudo, Gerard ; DeSalvo, Barbara ; Perniola, Luca
Author_Institution :
Univ. Grenoble Alpes, Grenoble, France
Volume :
62
Issue :
8
fYear :
2015
fDate :
Aug. 2015
Firstpage :
2494
Lastpage :
2501
Abstract :
In this paper, the use of HfO2-based oxide-based resistive memory (OxRAM) devices operated in binary mode to implement synapses in a convolutional neural network (CNN) is studied. We employed an artificial synapse composed of multiple OxRAM cells connected in parallel, thereby providing synaptic efficacies. Electrical characterization results show that the proposed HfO2-based OxRAM technology offers good electrical properties in terms of endurance (>108 cycles), speed (<;10 ns), and low energy (<;10 pJ), and thus being well suited for neuromorphic applications. A device physical model is developed in order to study the variability of the resistance as a function of the stochastic position of oxygen vacancies in 3-D. Finally, the proposed binary OxRAM synapse has been used for CNN system-level simulations. High accuracy (recognition rate > 98%) is demonstrated for a complex visual pattern recognition application. We demonstrated that the resistance variability and the reduced memory window of the OxRAM cells when operated at extremely low programming conditions (<;10 pJ per switching event) have a small impact on the performances of proposed OxRAM-based CNN (recognition rate 94%).
Keywords :
hafnium compounds; neural nets; resistive RAM; vacancies (crystal); CNN system-level simulations; HfO2-based OxRAM devices; HfO2-based oxide-based resistive memory devices; HfO2; OxRAM-based CNN; artificial synapse; binary OxRAM synapse; binary mode; convolutional neural network; electrical characterization; neuromorphic applications; oxygen vacancies; reduced memory window; resistance variability; stochastic position; synaptic efficacies; visual pattern recognition application; Hafnium compounds; Immune system; Integrated circuits; Neurons; Programming; Resistance; Switches; Convolutional neural network (CNN); resistive RAM (RRAM) synapse; spike timing-dependent plasticity (STDP); stochastic neuromorphic system; visual pattern extraction; visual pattern extraction.;
fLanguage :
English
Journal_Title :
Electron Devices, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9383
Type :
jour
DOI :
10.1109/TED.2015.2440102
Filename :
7124442
Link To Document :
بازگشت