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

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

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 d...

Full description

Bibliographic Details
Main Authors: Ambrogio, Stefano, Ciocchini, Nicola, Laudato, Mario, Milo, Valerio, Pirovano, Agostino, Fantini, Paolo, Ielmini, Daniele
Format: Online
Language:English
Published: Frontiers Media S.A. 2016
Online Access:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4781832/
id pubmed-4781832
recordtype oai_dc
spelling pubmed-47818322016-03-24 Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses Ambrogio, Stefano Ciocchini, Nicola Laudato, Mario Milo, Valerio Pirovano, Agostino Fantini, Paolo Ielmini, Daniele Neuroscience 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. Frontiers Media S.A. 2016-03-08 /pmc/articles/PMC4781832/ /pubmed/27013934 http://dx.doi.org/10.3389/fnins.2016.00056 Text en Copyright © 2016 Ambrogio, Ciocchini, Laudato, Milo, Pirovano, Fantini and Ielmini. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
repository_type Open Access Journal
institution_category Foreign Institution
institution US National Center for Biotechnology Information
building NCBI PubMed
collection Online Access
language English
format Online
author Ambrogio, Stefano
Ciocchini, Nicola
Laudato, Mario
Milo, Valerio
Pirovano, Agostino
Fantini, Paolo
Ielmini, Daniele
spellingShingle Ambrogio, Stefano
Ciocchini, Nicola
Laudato, Mario
Milo, Valerio
Pirovano, Agostino
Fantini, Paolo
Ielmini, Daniele
Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses
author_facet Ambrogio, Stefano
Ciocchini, Nicola
Laudato, Mario
Milo, Valerio
Pirovano, Agostino
Fantini, Paolo
Ielmini, Daniele
author_sort Ambrogio, Stefano
title Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses
title_short Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses
title_full Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses
title_fullStr Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses
title_full_unstemmed Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses
title_sort unsupervised learning by spike timing dependent plasticity in phase change memory (pcm) synapses
description 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.
publisher Frontiers Media S.A.
publishDate 2016
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4781832/
_version_ 1613548456241004544

Similar Items