Neuromorphic Computing with Multi-memristive Synapses

Overview

Journal Nat Commun

Specialty Biology

Date 2018 Jun 30

PMID 29955057

Citations 90

Authors

Irem Boybat

Manuel Le Gallo

S R Nandakumar

Timoleon Moraitis

Thomas Parnell

Tomas Tuma

Bipin Rajendran

Yusuf Leblebici

Abu Sebastian

Evangelos Eleftheriou

Affiliations

Soon will be listed here.

Abstract

Neuromorphic computing has emerged as a promising avenue towards building the next generation of intelligent computing systems. It has been proposed that memristive devices, which exhibit history-dependent conductivity modulation, could efficiently represent the synaptic weights in artificial neural networks. However, precise modulation of the device conductance over a wide dynamic range, necessary to maintain high network accuracy, is proving to be challenging. To address this, we present a multi-memristive synaptic architecture with an efficient global counter-based arbitration scheme. We focus on phase change memory devices, develop a comprehensive model and demonstrate via simulations the effectiveness of the concept for both spiking and non-spiking neural networks. Moreover, we present experimental results involving over a million phase change memory devices for unsupervised learning of temporal correlations using a spiking neural network. The work presents a significant step towards the realization of large-scale and energy-efficient neuromorphic computing systems.

Citing Articles

A mixed-precision memristor and SRAM compute-in-memory AI processor.

Khwa W, Wen T, Hsu H, Huang W, Chang Y, Chiu T Nature. 2025; .

PMID: 40044859 DOI: 10.1038/s41586-025-08639-2.

Photonic (computational) memories: tunable nanophotonics for data storage and computing.

Lian C, Vagionas C, Alexoudi T, Pleros N, Youngblood N, Rios C Nanophotonics. 2024; 11(17):3823-3854.

PMID: 39635175 PMC: 11501226. DOI: 10.1515/nanoph-2022-0089.

Probabilistic metaplasticity for continual learning with memristors in spiking networks.

Zohora F, Karia V, Soures N, Kudithipudi D Sci Rep. 2024; 14(1):29496.

PMID: 39604461 PMC: 11603065. DOI: 10.1038/s41598-024-78290-w.

An overview of critical applications of resistive random access memory.

Zahoor F, Nisar A, Bature U, Abbas H, Bashir F, Chattopadhyay A Nanoscale Adv. 2024; .

PMID: 39263252 PMC: 11382421. DOI: 10.1039/d4na00158c.

Crossmodal sensory neurons based on high-performance flexible memristors for human-machine in-sensor computing system.

Li Z, Li Z, Tang W, Yao J, Dou Z, Gong J Nat Commun. 2024; 15(1):7275.

PMID: 39179548 PMC: 11344147. DOI: 10.1038/s41467-024-51609-x.

References

Saighi S, Mayr C, Serrano-Gotarredona T, Schmidt H, Lecerf G, Tomas J . Plasticity in memristive devices for spiking neural networks. Front Neurosci. 2015; 9:51. PMC: 4345885. DOI: 10.3389/fnins.2015.00051. View

Malenka R, Bear M . LTP and LTD: an embarrassment of riches. Neuron. 2004; 44(1):5-21. DOI: 10.1016/j.neuron.2004.09.012. View

Covi E, Brivio S, Serb A, Prodromakis T, Fanciulli M, Spiga S . Analog Memristive Synapse in Spiking Networks Implementing Unsupervised Learning. Front Neurosci. 2016; 10:482. PMC: 5078263. DOI: 10.3389/fnins.2016.00482. View

Bolshakov V, Golan H, Kandel E, Siegelbaum S . Recruitment of new sites of synaptic transmission during the cAMP-dependent late phase of LTP at CA3-CA1 synapses in the hippocampus. Neuron. 1997; 19(3):635-51. DOI: 10.1016/s0896-6273(00)80377-3. View

Alibart F, Zamanidoost E, Strukov D . Pattern classification by memristive crossbar circuits using ex situ and in situ training. Nat Commun. 2013; 4:2072. DOI: 10.1038/ncomms3072. View

Koelmans W, Sebastian A, Jonnalagadda V, Krebs D, Dellmann L, Eleftheriou E . Projected phase-change memory devices. Nat Commun. 2015; 6:8181. PMC: 4569800. DOI: 10.1038/ncomms9181. View

Edwards F . Neurobiology. LTP is a long term problem. Nature. 1991; 350(6316):271-2. DOI: 10.1038/350271a0. View

Wang Z, Joshi S, Savelev S, Jiang H, Midya R, Lin P . Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing. Nat Mater. 2016; 16(1):101-108. DOI: 10.1038/nmat4756. View

Tuma T, Pantazi A, Le Gallo M, Sebastian A, Eleftheriou E . Stochastic phase-change neurons. Nat Nanotechnol. 2016; 11(8):693-9. DOI: 10.1038/nnano.2016.70. View

10.

Mostafa H, Khiat A, Serb A, Mayr C, Indiveri G, Prodromakis T . Implementation of a spike-based perceptron learning rule using TiO2-x memristors. Front Neurosci. 2015; 9:357. PMC: 4591430. DOI: 10.3389/fnins.2015.00357. View

11.

Wong H, Salahuddin S . Memory leads the way to better computing. Nat Nanotechnol. 2015; 10(3):191-4. DOI: 10.1038/nnano.2015.29. View

12.

Malenka R, Nicoll R . Long-term potentiation--a decade of progress?. Science. 1999; 285(5435):1870-4. DOI: 10.1126/science.285.5435.1870. View

13.

Sebastian A, Tuma T, Papandreou N, Le Gallo M, Kull L, Parnell T . Temporal correlation detection using computational phase-change memory. Nat Commun. 2017; 8(1):1115. PMC: 5653661. DOI: 10.1038/s41467-017-01481-9. View

14.

Fuller E, El Gabaly F, Leonard F, Agarwal S, Plimpton S, Jacobs-Gedrim R . Li-Ion Synaptic Transistor for Low Power Analog Computing. Adv Mater. 2016; 29(4). DOI: 10.1002/adma.201604310. View

15.

Sebastian A, Le Gallo M, Krebs D . Crystal growth within a phase change memory cell. Nat Commun. 2014; 5:4314. DOI: 10.1038/ncomms5314. View

16.

Qiao N, Mostafa H, Corradi F, Osswald M, Stefanini F, Sumislawska D . A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses. Front Neurosci. 2015; 9:141. PMC: 4413675. DOI: 10.3389/fnins.2015.00141. View

17.

van de Burgt Y, Lubberman E, Fuller E, Keene S, Faria G, Agarwal S . A non-volatile organic electrochemical device as a low-voltage artificial synapse for neuromorphic computing. Nat Mater. 2017; 16(4):414-418. DOI: 10.1038/nmat4856. View

18.

Benke T, Luthi A, Isaac J, Collingridge G . Modulation of AMPA receptor unitary conductance by synaptic activity. Nature. 1998; 393(6687):793-7. DOI: 10.1038/31709. View

19.

Boyn S, Grollier J, Lecerf G, Xu B, Locatelli N, Fusil S . Learning through ferroelectric domain dynamics in solid-state synapses. Nat Commun. 2017; 8:14736. PMC: 5382254. DOI: 10.1038/ncomms14736. View

20.

Ambrogio S, Ciocchini N, Laudato M, Milo V, Pirovano A, Fantini P . Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses. Front Neurosci. 2016; 10:56. PMC: 4781832. DOI: 10.3389/fnins.2016.00056. View