Intelligent Memories that Perform Inference with the Physics of Nanodevices

Informazioni relative al progetto

NANOINFER

ID dell’accordo di sovvenzione: 715872

DOI

10.3030/715872

Progetto chiuso

Data della firma CE 12 Dicembre 2016

Data di avvio 1 Marzo 2017

Data di completamento 31 Agosto 2023

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 499 609,00

Contributo UE

€ 1 499 609,00

Coordinato da

CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRS
France

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Conference proceedings (16)

Training Dynamical Binary Neural Networks with Equilibrium Propagation

Autori: Laydevant, Jérémie; Ernoult, Maxence; Querlioz, Damien; Grollier, Julie
Pubblicato in: Computer Vision and Pattern Recognition (CVPR), 2021, ISBN 978-1-7281-7168-5
Editore: IEEE
DOI: 10.1109/cvprw53098.2021.00522

A Multimode Hybrid Memristor-CMOS Prototyping Platform Supporting Digital and Analog Projects

Autori: K.-E. Harabi; C. Turck; M. Drouhin; A. Renaudineau; T. Bersani-Veroni; D. Querlioz; T. Hirtzlin; E. Vianello; M Bocquet; J.-M. Portal
Pubblicato in: ASP-DAC, Numero 8, 2023
Editore: ACM
DOI: 10.1145/3566097.3567944

Energy-Efficient Bayesian Inference Using Near-Memory Computation with Memristors

Autori: C. Turck; K.-E. Harabi; T. Hirtzlin; E. Vianello; R. Laurent; J. Droulez; P. Bessiere; M. Bocquet; J.-M. Portal; D. Querlioz
Pubblicato in: DATE, Numero 8, 2023
Editore: ACM
DOI: 10.23919/date56975.2023.10137312

Low Power In-Memory Implementation of Ternary Neural Networks with Resistive RAM-Based Synapse

Autori: A. Laborieux, M. Bocquet, T. Hirtzlin, J.-O. Klein, L. Herrera Diez, E. Nowak, E. Vianello, J.-M. Portal, D. Querlioz
Pubblicato in: 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), 2020, Pagina/e 136-140, ISBN 978-1-7281-4922-6
Editore: IEEE
DOI: 10.1109/aicas48895.2020.9073877

Embracing the Unreliability of Memory Devices for Neuromorphic Computing

Autori: Marc Bocquet; Tifenn Hirtzlin; Jacques-Olivier Klein; Etienne Nowak; Elisa Vianello; Jean-Michel Portal; Damien Querlioz
Pubblicato in: IRPS, Numero 5, 2020, ISBN 978-1-7281-3199-3
Editore: IEEE
DOI: 10.1109/irps45951.2020.9128346

Hybrid Analog-Digital Learning with Differential RRAM Synapses

Autori: Hirtzlin, T.; Bocquet, Marc; Ernoult, M.; Klein, J.-O; Nowak, E.; Vianello, E.; Portal, J.-M; Querlioz, D.
Pubblicato in: 2019 IEEE International Electron Devices Meeting (IEDM), Dec 2019, San Francisco, United States, Numero 2, 2019
Editore: IEEE

Low-Overhead Implementation of Binarized Neural Networks Employing Robust 2T2R Resistive RAM Bridges

Autori: M. Ezzadeen; A. Majumdar; Marc Bocquet; Bastien Giraud; J.-P. Noel; Francois Andrieu; Damien Querlioz; J-M. Portal
Pubblicato in: ESSCIRC, Numero 10, 2021
Editore: IEEE
DOI: 10.1109/essderc53440.2021.9631381

Use of Magnetoresistive Random-Access Memory as Approximate Memory for Training Neural Networks

Autori: Nicolas Locatelli, Adrien F. Vincent, Damien Querlioz
Pubblicato in: 2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS), 2018, Pagina/e 553-556, ISBN 978-1-5386-9562-3
Editore: IEEE
DOI: 10.1109/icecs.2018.8617952

Circuit-Level Evaluation of the Generation of Truly Random Bits with Superparamagnetic Tunnel Junctions

Autori: Damir Vodenicarevic, Nicolas Locatelli, Alice Mizrahi, Tifenn Hirtzlin, Joseph S. Friedman, Julie Grollier, Damien Querlioz
Pubblicato in: 2018 IEEE International Symposium on Circuits and Systems (ISCAS), 2018, Pagina/e 1-4, ISBN 978-1-5386-4881-0
Editore: IEEE
DOI: 10.1109/iscas.2018.8351771

In-Memory and Error-Immune Differential RRAM Implementation of Binarized Deep Neural Networks

Autori: M. Bocquet, T. Hirztlin, J.-O. Klein, E. Nowak, E. Vianello, J.-M. Portal, D. Querlioz
Pubblicato in: 2018 IEEE International Electron Devices Meeting (IEDM), 2018, Pagina/e 20.6.1-20.6.4, ISBN 978-1-7281-1987-8
Editore: IEEE
DOI: 10.1109/iedm.2018.8614639

Outstanding Bit Error Tolerance of Resistive RAM-Based Binarized Neural Networks

Autori: T. Hirtzlin, M. Bocquet, J.-O. Klein, E. Nowak, E. Vianello, J.-M. Portal, D. Querlioz
Pubblicato in: 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), 2019, Pagina/e 288-292, ISBN 978-1-5386-7884-8
Editore: IEEE
DOI: 10.1109/aicas.2019.8771544

Implementing Binarized Neural Networks with Magnetoresistive RAM without Error Correction

Autori: Tifenn Hirtzlin, Bogdan Penkovsky, Jacques-Olivier Klein, Nicolas Locatelli, Adrien F. Vincent, Marc Bocquet, Jean-Michel Portal, Damien Querlioz
Pubblicato in: 2019 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH), 2019, Pagina/e 1-5, ISBN 978-1-7281-5520-3
Editore: IEEE
DOI: 10.1109/nanoarch47378.2019.181300

Memory-Centric Neuromorphic Computing With Nanodevices

Autori: Damien Querlioz, Julie Grollier, Tifenn Hirtzlin, Jacques-Olivier Klein, Etienne Nowak, Elisa Vianello, Marc Bocquet, Jean-Michel Portal, Miguel Romera, Philippe Talatchian
Pubblicato in: 2019 IEEE Biomedical Circuits and Systems Conference (BioCAS), 2019, Pagina/e 1-4, ISBN 978-1-5090-0617-5
Editore: IEEE
DOI: 10.1109/BIOCAS.2019.8919010

Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input

Autori: Maxence Ernoult, Julie Grollier, Damien Querlioz, Yoshua Bengio, Benjamin Scellier
Pubblicato in: Advances in Neural Information Processing Systems 32 (NIPS 2019), 2019
Editore: Neural Information Processing Systems

In-Memory Resistive RAM Implementation of Binarized Neural Networks for Medical Applications

Autori: Bogdan Penkovsky, Marc Bocquet, Tifenn Hirtzlin, Jacques-Olivier Klein, Etienne Nowak, Elisa Vianello, Jean-Michel Portal, Damien Querlioz
Pubblicato in: 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2020, Pagina/e 690-695, ISBN 978-3-9819263-4-7
Editore: IEEE
DOI: 10.23919/date48585.2020.9116439

CAPC: A Configurable Analog Pop-Count Circuit for Near-Memory Binary Neural Networks

Autori: F. Jebali; A. Majumdar; Axel Laborieux; Tifenn Hirtzlin; E. Vianello; J.P. Walder; Marc Bocquet; Damien Querlioz; Jean-Michel Portal
Pubblicato in: https://hal.science/hal-03624922, Numero 12, 2021
Editore: IEEE
DOI: 10.1109/mwscas47672.2021.9531919

Peer reviewed articles (19)

Model of the Weak Reset Process in HfO x Resistive Memory for Deep Learning Frameworks

Autori: Atreya Majumdar; Marc Bocquet; Tifenn Hirtzlin; Axel Laborieux; Jacques-Olivier Klein; Etienne Nowak; Elisa Vianello; Jean-Michel Portal; Damien Querlioz
Pubblicato in: IEEE Transactions on Electron Devices, Numero 2, 2021, ISSN 0018-9383
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/ted.2021.3108479

Hardware-Efficient Stochastic Binary CNN Architectures for Near-Sensor Computing

Autori: Vivek Parmar, Bogdan Penkovsky, Damien Querlioz, Manan Suri
Pubblicato in: Frontiers in Neuroscience, 2022, ISSN 1662-453X
Editore: Frontiers
DOI: 10.3389/fnins.2021.781786

Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing Its Gradient Estimator Bias

Autori: Axel Laborieux; Maxence Ernoult; Maxence Ernoult; Maxence Ernoult; Benjamin Scellier; Yoshua Bengio; Yoshua Bengio; Julie Grollier; Damien Querlioz
Pubblicato in: Frontiers in Neuroscience, Numero 7, 2021, ISSN 1662-453X
Editore: Frontiers
DOI: 10.3389/fnins.2021.633674

In-situ learning harnessing intrinsic resistive memory variability through Markov Chain Monte Carlo Sampling

Autori: Dalgaty, Thomas; Castellani, Niccolo; Querlioz, Damien; Vianello, Elisa
Pubblicato in: Nature Electronics, Numero 3, 2021, ISSN 2520-1131
Editore: Nature
DOI: 10.1038/s41928-020-00523-3

Synaptic metaplasticity in binarized neural networks

Autori: Axel Laborieux; Maxence Ernoult; Tifenn Hirtzlin; Damien Querlioz
Pubblicato in: Nature Communications, 2021, ISSN 2041-1723
Editore: Nature Publishing Group
DOI: 10.1038/s41467-021-22768-y

Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations

Autori: Xing Chen, Flavio Abreu Araujo, Mathieu Riou, Jacob Torrejon, Dafiné Ravelosona, Wang Kang, Weisheng Zhao, Julie Grollier, Damien Querlioz
Pubblicato in: Nature Communications, 2022, ISSN 2041-1723
Editore: Nature Publishing Group
DOI: 10.1038/s41467-022-28571-7

Bringing uncertainty quantification to the extreme-edge with memristor-based Bayesian neural networks

Autori: Djohan Bonnet; Tifenn Hirtzlin; Atreya Majumdar; Thomas Dalgaty; Eduardo Esmanhotto; Valentina Meli; Niccolò Castellani; Simon Martin; Jean-Francois Nodin; Guillaume Bourgeois; Jean-Michel Portal; Damien Querlioz; Elisa Vianello
Pubblicato in: Nature Communications, Numero 14, 2023, Pagina/e 7530, ISSN 2041-1723
Editore: Nature Publishing Group
DOI: 10.1038/s41467-023-43317-9

Physics for Neuromorphic Computing

Autori: Markovic, Danijela; Mizrahi, Alice; Querlioz, Damien; Grollier, Julie
Pubblicato in: Nature Reviews Physics, Numero 6, 2020, ISSN 2522-5820
Editore: Nature

Ex Situ Transfer of Bayesian Neural Networks to Resistive Memory‐Based Inference Hardware

Autori: Thomas Dalgaty; Eduardo Esmanhotto; Niccolo Castellani; Damien Querlioz; Elisa Vianello
Pubblicato in: Advanced Intelligent Systems, Numero 1, 2021, ISSN 2640-4567
Editore: WIley
DOI: 10.1002/aisy.202000103

Characterization and modeling of spiking and bursting in experimental NbO_x neuron

Autori: Marie Drouhin; Shuai Li; Matthieu Grelier; Sophie Collin; Florian Godel; Robert G Elliman; Bruno Dlubak; Juan Trastoy; Damien Querlioz; Julie Grollier
Pubblicato in: Crossref, Numero 1, 2022, ISSN 2634-4386
Editore: IOP
DOI: 10.1088/2634-4386/ac969a

Spintronics for neuromorphic computing

Autori: Grollier, J.; Querlioz, D.; Camsari, K. Y.; Everschor-Sitte, K.; Fukami, S.; Stiles, M. D.
Pubblicato in: Nature Electronics, 2020, ISSN 2520-1131
Editore: Nature
DOI: 10.1038/s41928-019-0360-9

Neural-like computing with populations of superparamagnetic basis functions

Autori: Alice Mizrahi, Tifenn Hirtzlin, Akio Fukushima, Hitoshi Kubota, Shinji Yuasa, Julie Grollier, Damien Querlioz
Pubblicato in: Nature Communications, Numero 9/1, 2018, ISSN 2041-1723
Editore: Nature Publishing Group
DOI: 10.1038/s41467-018-03963-w

Low-Energy Truly Random Number Generation with Superparamagnetic Tunnel Junctions for Unconventional Computing

Autori: D. Vodenicarevic, N. Locatelli, A. Mizrahi, J. S. Friedman, A. F. Vincent, M. Romera, A. Fukushima, K. Yakushiji, H. Kubota, S. Yuasa, S. Tiwari, J. Grollier, D. Querlioz
Pubblicato in: Physical Review Applied, Numero 8/5, 2017, ISSN 2331-7019
Editore: APS
DOI: 10.1103/physrevapplied.8.054045

Using Memristors for Robust Local Learning of Hardware Restricted Boltzmann Machines

Autori: Maxence Ernoult, Julie Grollier, Damien Querlioz
Pubblicato in: Scientific Reports, Numero 9/1, 2019, ISSN 2045-2322
Editore: Nature Publishing Group
DOI: 10.1038/s41598-018-38181-3

Contrasting Advantages of Learning With Random Weights and Backpropagation in Non-Volatile Memory Neural Networks

Autori: Christopher H. Bennett, Vivek Parmar, Laurie E. Calvet, Jacques-Olivier Klein, Manan Suri, Matthew J. Marinella, Damien Querlioz
Pubblicato in: IEEE Access, Numero 7, 2019, Pagina/e 73938-73953, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2019.2920076

Stochastic Computing for Hardware Implementation of Binarized Neural Networks

Autori: Tifenn Hirtzlin, Bogdan Penkovsky, Marc Bocquet, Jacques-Olivier Klein, Jean-Michel Portal, Damien Querlioz
Pubblicato in: IEEE Access, Numero 7, 2019, Pagina/e 76394-76403, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2019.2921104

Digital Biologically Plausible Implementation of Binarized Neural Networks With Differential Hafnium Oxide Resistive Memory Arrays

Autori: Tifenn Hirtzlin, Marc Bocquet, Bogdan Penkovsky, Jacques-Olivier Klein, Etienne Nowak, Elisa Vianello, Jean-Michel Portal, Damien Querlioz
Pubblicato in: Frontiers in Neuroscience, Numero 13, 2020, ISSN 1662-453X
Editore: Frontiers
DOI: 10.3389/fnins.2019.01383

A memristor-based Bayesian machine

Autori: Kamel-Eddine Harabi, Tifenn Hirtzlin, Clément Turck, Elisa Vianello, Raphaël Laurent, Jacques Droulez, Pierre Bessière, Jean-Michel Portal, Marc Bocquet, Damien Querlioz
Pubblicato in: Nature Electronics, 2023, ISSN 2520-1131
Editore: Springer Nature
DOI: 10.1038/s41928-022-00886-9

Implementation of Ternary Weights With Resistive RAM Using a Single Sense Operation Per Synapse

Autori: Axel Laborieux; Marc Bocquet; Tifenn Hirtzlin; Jacques-Olivier Klein; Etienne Nowak; Elisa Vianello; Jean-Michel Portal; Damien Querlioz
Pubblicato in: IEEE Transactions on Circuits and Systems I: Regular Papers, Numero 7, 2021, ISSN 1549-8328
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tcsi.2020.3031627