Combining Accuracy and Plasticity in Convolutional Neural Networks Based on Resistive Memory Arrays for Autonomous Learning

Autor: Stefano Bianchi, Irene Munoz-Martin, Erika Covi, Alessandro Bricalli, Giuseppe Piccoloni, Amir Regev, Gabriel Molas, Jean Francois Nodin, Francois Andrieu, Daniele Ielmini

Publikováno v: IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, Vol 7, Iss 2, Pp 132-140 (2021)

Nowadays, artificial neural networks (ANNs) can outperform the human brain’s ability in specific tasks. However, ANNs cannot replicate the efficient and low-power learning, adaptation, and consolidation typical of biological organisms. Here, we pre

Externí odkaz: https://doaj.org/article/37b5a4a1ad6f48178c41617d2bac5f0f

Combining Accuracy and Plasticity in Convolutional Neural Networks Based on Resistive Memory Arrays for Autonomous Learning

Autor: Alessandro Bricalli, Daniele Ielmini, Jean Francois Nodin, Giuseppe Piccoloni, Francois Andrieu, Amir Regev, S. Bianchi, Irene Munoz-Martin, Erika Covi, Gabriel Molas

Publikováno v: IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, Vol 7, Iss 2, Pp 132-140 (2021)

Nowadays, artificial neural networks (ANNs) can outperform the human brain’s ability in specific tasks. However, ANNs cannot replicate the efficient and low-power learning, adaptation, and consolidation typical of biological organisms. Here, we pre

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bb8052fe6cc502781ba3322cf20b20b0
https://doi.org/10.1109/jxcdc.2021.3118061

Fully-Integrated Spiking Neural Network Using SiOx-Based RRAM as Synaptic Device

Autor: Alexandre Valentian, Amir Regev, Thomas Mesquida, Alessandro Bricalli, G. Piccolboni, Jean-Francois Nodin, Gabriel Molas

Publikováno v: AICAS

This paper presents, to the best of the authors’ knowledge, the first complete integration of a Spiking Neural Network combining analog neurons and SiO x -based resistive memory (RRAM) synapses. The implemented topology is a perceptron, and the cir

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::133955bd0907cf7acf743f78934ed324
https://doi.org/10.1109/aicas48895.2020.9073840

(Invited) Resistive Memories (RRAM) Variability: Challenges and Solutions

Autor: Philippe Blaise, Cecile Nail, E. Nowak, Gabriel Molas, Jean Coignus, Carlo Cagli, Gilbert Sassine, Diego Alfaro Robayo, Jean-Francois Nodin

Publikováno v: ECS Transactions. 86:35-47

In this work, we address Resistive RAM (RRAM) variability. To this aim, we investigate various RRAM technologies (Oxide RAM and Conductive Bridging RAM), integrated on kb 1T1R arrays. Impact of variability is evaluated and discussed for various RRAM

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2dff6491f3ab75a907081fd621a3b4bf
https://doi.org/10.1149/08603.0035ecst

Statistical analysis of CBRAM endurance

Autor: Gilbert Sassine, G. Molas, Q. Raffay, D. Alfaro Robayo, E. Nowak, Cecile Nail, Mathieu Bernard, Gerard Ghibaudo, Jean-Francois Nodin

Publikováno v: Proecedings of the 2018 International Symposium on VLSI Technology, Systems and Application (VLSI-TSA)
2018 International Symposium on VLSI Technology, Systems and Application (VLSI-TSA)
2018 International Symposium on VLSI Technology, Systems and Application (VLSI-TSA), Apr 2018, Hsinchu, Taiwan. pp.115-116, ⟨10.1109/VLSI-TSA.2018.8403856⟩

session T6: RRAM; International audience; In this paper, we address endurance reliability of resistive RAM at array level. To this aim, Al 2 O 3 based Conductive Bridging RAM (CBRAM) kb arrays are studied. Maximum number of cycles the memory can sust

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f538c4e82403e202dd6691e04c99e0d
https://hal.archives-ouvertes.fr/hal-02050364