Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses

Overview

Journal Front Neurosci

Date 2016 Mar 26

PMID 27013934

Citations 30

Authors

Stefano Ambrogio

Nicola Ciocchini

Mario Laudato

Valerio Milo

Agostino Pirovano

Paolo Fantini

Daniele Ielmini

Affiliations

Soon will be listed here.

Abstract

We present a novel one-transistor/one-resistor (1T1R) synapse for neuromorphic networks, based on phase change memory (PCM) technology. The synapse is capable of spike-timing dependent plasticity (STDP), where gradual potentiation relies on set transition, namely crystallization, in the PCM, while depression is achieved via reset or amorphization of a chalcogenide active volume. STDP characteristics are demonstrated by experiments under variable initial conditions and number of pulses. Finally, we support the applicability of the 1T1R synapse for learning and recognition of visual patterns by simulations of fully connected neuromorphic networks with 2 or 3 layers with high recognition efficiency. The proposed scheme provides a feasible low-power solution for on-line unsupervised machine learning in smart reconfigurable sensors.

Citing Articles

Scalable Microscale Artificial Synapses of Lead Halide Perovskite with Femtojoule Energy Consumption.

de Boer J, Ehrler B ACS Energy Lett. 2024; 9(12):5787-5794.

PMID: 39698340 PMC: 11650764. DOI: 10.1021/acsenergylett.4c02360.

Synchronized stepwise control of firing and learning thresholds in a spiking randomly connected neural network toward hardware implementation.

Nomura K, Nishi Y Front Neurosci. 2024; 18:1402646.

PMID: 39605789 PMC: 11599226. DOI: 10.3389/fnins.2024.1402646.

A scalable solution recipe for a Ag-based neuromorphic device.

Rao T, Mondal I, Bannur B, Kulkarni G Discov Nano. 2023; 18(1):124.

PMID: 37812259 PMC: 10562349. DOI: 10.1186/s11671-023-03906-5.

Ionic-electronic halide perovskite memdiodes enabling neuromorphic computing with a second-order complexity.

John R, Milozzi A, Tsarev S, Bronnimann R, Boehme S, Wu E Sci Adv. 2022; 8(51):eade0072.

PMID: 36563153 PMC: 9788778. DOI: 10.1126/sciadv.ade0072.

Voltage-dependent synaptic plasticity: Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential.

Garg N, Balafrej I, Stewart T, Portal J, Bocquet M, Querlioz D Front Neurosci. 2022; 16:983950.

PMID: 36340782 PMC: 9634260. DOI: 10.3389/fnins.2022.983950.

References

Yu S, Gao B, Fang Z, Yu H, Kang J, Wong H . A low energy oxide-based electronic synaptic device for neuromorphic visual systems with tolerance to device variation. Adv Mater. 2013; 25(12):1774-9. DOI: 10.1002/adma.201203680. View

Ambrogio S, Balatti S, Nardi F, Facchinetti S, Ielmini D . Spike-timing dependent plasticity in a transistor-selected resistive switching memory. Nanotechnology. 2013; 24(38):384012. DOI: 10.1088/0957-4484/24/38/384012. View

Locatelli N, Cros V, Grollier J . Spin-torque building blocks. Nat Mater. 2013; 13(1):11-20. DOI: 10.1038/nmat3823. View

Cassinerio M, Ciocchini N, Ielmini D . Logic computation in phase change materials by threshold and memory switching. Adv Mater. 2013; 25(41):5975-80. DOI: 10.1002/adma.201301940. View

Thomas A, Niehorster S, Fabretti S, Shepheard N, Kuschel O, Kupper K . Tunnel junction based memristors as artificial synapses. Front Neurosci. 2015; 9:241. PMC: 4493388. DOI: 10.3389/fnins.2015.00241. View

Waser R, Aono M . Nanoionics-based resistive switching memories. Nat Mater. 2007; 6(11):833-40. DOI: 10.1038/nmat2023. View

Wright C, Liu Y, Kohary K, Aziz M, Hicken R . Arithmetic and biologically-inspired computing using phase-change materials. Adv Mater. 2011; 23(30):3408-13. PMC: 3715110. DOI: 10.1002/adma.201101060. View

Jo S, Chang T, Ebong I, Bhadviya B, Mazumder P, Lu W . Nanoscale memristor device as synapse in neuromorphic systems. Nano Lett. 2010; 10(4):1297-301. DOI: 10.1021/nl904092h. View

Ohno T, Hasegawa T, Tsuruoka T, Terabe K, Gimzewski J, Aono M . Short-term plasticity and long-term potentiation mimicked in single inorganic synapses. Nat Mater. 2011; 10(8):591-5. DOI: 10.1038/nmat3054. View

10.

Eryilmaz S, Kuzum D, Jeyasingh R, Kim S, BrightSky M, Lam C . Brain-like associative learning using a nanoscale non-volatile phase change synaptic device array. Front Neurosci. 2014; 8:205. PMC: 4106403. DOI: 10.3389/fnins.2014.00205. View

11.

Wang Z, Ambrogio S, Balatti S, Ielmini D . A 2-transistor/1-resistor artificial synapse capable of communication and stochastic learning in neuromorphic systems. Front Neurosci. 2015; 8:438. PMC: 4295533. DOI: 10.3389/fnins.2014.00438. View

12.

Vincent A, Larroque J, Locatelli N, Ben Romdhane N, Bichler O, Gamrat C . Spin-transfer torque magnetic memory as a stochastic memristive synapse for neuromorphic systems. IEEE Trans Biomed Circuits Syst. 2015; 9(2):166-74. DOI: 10.1109/TBCAS.2015.2414423. View

13.

Kuzum D, Jeyasingh R, Lee B, Wong H . Nanoelectronic programmable synapses based on phase change materials for brain-inspired computing. Nano Lett. 2011; 12(5):2179-86. DOI: 10.1021/nl201040y. View

14.

Bi G, Poo M . Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J Neurosci. 1998; 18(24):10464-72. PMC: 6793365. View

15.

Indiveri G, Linares-Barranco B, Legenstein R, Deligeorgis G, Prodromakis T . Integration of nanoscale memristor synapses in neuromorphic computing architectures. Nanotechnology. 2013; 24(38):384010. DOI: 10.1088/0957-4484/24/38/384010. View

16.

Prezioso M, Merrikh-Bayat F, Hoskins B, Adam G, Likharev K, Strukov D . Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature. 2015; 521(7550):61-4. DOI: 10.1038/nature14441. View