CoChat

Training a Probabilistic Graphical Model With Resistive Switching Electronic Synapses

Open access
Eryilmaz, Sukru Burc, Neftci, Emre, Joshi, Siddharth, Kim, SangBum, BrightSky, Matthew, Lung, Hsiang-Lan, Lam, Chung, Cauwenberghs, Gert, Wong, Hon-Sum Philip · 2016 · IEEE Transactions on Electron Devices

The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.

Abstract

Current large-scale implementations of deep learning and data mining require thousands of processors, massive amounts of off-chip memory, and consume gigajoules of energy. New memory technologies, such as nanoscale two-terminal resistive switching memory devices, offer a compact, scalable, and low-power alternative that permits on-chip colocated processing and memory in fine-grain distributed parallel architecture. Here, we report the first use of resistive memory devices for implementing and training a restricted Boltzmann machine (RBM), a generative probabilistic graphical model as a key component for unsupervised learning in deep networks. We experimentally demonstrate a 45-synapse RBM realized with 90 resistive phase change memory (PCM) elements trained with a bioinspired variant of the contrastive divergence algorithm, implementing Hebbian and anti-Hebbian weight updates. The resistive PCM devices show a twofold to tenfold reduction in error rate in a missing pixel pattern completion task trained over 30 epochs, compared with untrained case. Measured programming energy consumption is 6.1 nJ per epoch with the PCM devices, a factor of ~ 150 times lower than the conventional processor-memory systems. We analyze and discuss the dependence of learning performance on cycle-to-cycle variations and number of gradual levels in the PCM analog memory devices.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/ted.2016.2616483

Cites

44 of 44 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 44 references

Research works printed but not linked: 9

  1. burr, 2014, Experimental demonstration and tolerancing of a large scale neural network, Proc IEEE IEDM, 29.5.1
  2. erhan, 2010, Why does unsupervised pre-training help deep learning?, J Mach Learn Res, 11, 625
  3. wong, 2016, Stanford Memory Trends
  4. shao, 2013, Energy characterization and instruction-level energy model of Intel’s Xeon Phi processor, Proc ISLPED, 389
  5. yu, 2012, 65k-neuron integrate and fire array transceiver with address-event reconfigurable synaptic routing, Proc IEEE Biomed Circuits Syst Conf (BioCAS), 21
  6. natarajan, 2014, A 14nm logic technology featuring 2nd-generation FinFET, air-gapped interconnects, self-aligned double patterning and a 0.0588 $\mu $ m2 SRAM cell size, Proc IEEE Int Electron Devices Meeting, 3.7.1
  7. 2016, 16-Channel Current-Input Analog-to-Digital Converter
  8. 2016, Dual current input 20-bit analog-to-digital converter
  9. mackay, 2003, Information Theory Inference and Learning Algorithms

Cited by

See all 34

Metadata

Authors
Eryilmaz, S. B., Neftci, E., Joshi, S., Kim, S., BrightSky, M., Lung, H.-L., Lam, C., Cauwenberghs, G., & Wong, H.-S. P.
Affiliations
  • Stanford University (US)
  • University of California, Irvine (US)
  • University of California San Diego (US)
  • IBM (United States) (US)
  • Macronix International (Taiwan) (TW)
Venue
IEEE Transactions on Electron Devices
Published
2016-12
Volume
63
Issue
12
Pages
5004-5011
ISSN
  • 0018-9383 (ISSN-L)
  • 1557-9646
OpenAlex
W2526812109
Cited by
34
References
44
Citations by year
2025: 1 · 2022: 5 · 2021: 3 · 2020: 6 · 2019: 8 · 2018: 8 · 2017: 3
FWCI
2.92
Type
journal article
Language
en
Open access
Locations
  • IEEE Transactions on Electron Devices (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • eScholarship (California Digital Library) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • SONIC, one of six centers of STARnet, a Semiconductor Research Corporation Program sponsored by MARCO and DARPA
  • NSF Expedition on Computing under Visual Cortex on Silicon (1317470)
  • Member Companies of the Stanford Non-Volatile Memory Technology Research Initiative and the Stanford SystemX Alliance
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Ferroelectric and Negative Capacitance Devices
  • Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Reservoir Computing
Keywords
resistive random access memory, phase-change memory, restricted Boltzmann machine, probabilistic graphical models, neuromorphic computing, contrastive divergence, Hebbian learning, unsupervised learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Training a Probabilistic Graphical Model With Resistive Switching Electronic Synapses. https://app.cochat.ai/papers/10.1109/ted.2016.2616483
The paper
Eryilmaz, S. B., Neftci, E., Joshi, S., Kim, S., BrightSky, M., Lung, H.-L., Lam, C., Cauwenberghs, G., & Wong, H.-S. P. (2016). Training a Probabilistic Graphical Model With Resistive Switching Electronic Synapses. IEEE Transactions on Electron Devices. https://doi.org/10.1109/ted.2016.2616483

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.