Next Article in Journal
Multichannel Inductive Sensor Based on Phase Division Multiplexing for Wear Debris Detection
Next Article in Special Issue
Effect of Electrode Material on the Crystallization of GeTe Grown by Atomic Layer Deposition for Phase Change Random Access Memory
Previous Article in Journal
A Decoupling Design with T-Shape Structure for the Aluminum Nitride Gyroscope
Previous Article in Special Issue
Artificial Neural Network for Response Inference of a Nonvolatile Resistance-Switch Array
Article Menu
Issue 4 (April) cover image

Export Article

Open AccessArticle

Partial-Gated Memristor Crossbar for Fast and Power-Efficient Defect-Tolerant Training

School of Electrical Engineering, Kookmin University, Seoul 02707, South Korea
*
Author to whom correspondence should be addressed.
Micromachines 2019, 10(4), 245; https://doi.org/10.3390/mi10040245
Received: 28 February 2019 / Revised: 9 April 2019 / Accepted: 12 April 2019 / Published: 13 April 2019
(This article belongs to the Special Issue Nanoscale Switches)
  |  
PDF [2699 KB, uploaded 23 April 2019]
  |  

Abstract

A real memristor crossbar has defects, which should be considered during the retraining time after the pre-training of the crossbar. For retraining the crossbar with defects, memristors should be updated with the weights that are calculated by the back-propagation algorithm. Unfortunately, programming the memristors takes a very long time and consumes a large amount of power, because of the incremental behavior of memristor’s program-verify scheme for the fine-tuning of memristor’s conductance. To reduce the programming time and power, the partial gating scheme is proposed here to realize the partial training, where only some part of neurons are trained, which are more responsible in the recognition error. By retraining the part, rather than the entire crossbar, the programming time and power of memristor crossbar can be significantly reduced. The proposed scheme has been verified by CADENCE circuit simulation with the real memristor’s Verilog-A model. When compared to retraining the entire crossbar, the loss of recognition rate of the partial gating scheme has been estimated only as small as 2.5% and 2.9%, for the MNIST and CIFAR-10 datasets, respectively. However, the programming time and power can be saved by 86% and 89.5% than the 100% retraining, respectively. View Full-Text
Keywords: memristor crossbar; partial-gated; fast and power-efficient training; defect-tolerant training memristor crossbar; partial-gated; fast and power-efficient training; defect-tolerant training
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Pham, K.V.; Nguyen, T.V.; Min, K.-S. Partial-Gated Memristor Crossbar for Fast and Power-Efficient Defect-Tolerant Training. Micromachines 2019, 10, 245.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Micromachines EISSN 2072-666X Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top