Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Neural Regulation01:37

Neural Regulation

40.4K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
40.4K
Weighted Mean00:57

Weighted Mean

5.4K
While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
5.4K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Opposing Estrous Cycle-Dependent Norepinephrine and Dopamine Regulation in Response to Methamphetamine.

Journal of neurochemistry·2026
Same author

Publisher Correction: Ultralow-voltage electrochemical organic light-emitting transistors with pinned and wide lateral recombination.

Nature materials·2026
Same author

Large Thermo- and Mechanosalient Actuation via Cooperative Twist Elasticity-Induced Packing Motif Conversion.

Journal of the American Chemical Society·2026
Same author

Halide-site-substituting spacer creates quasi-two-dimensional perovskites for vapour-deposited light-emitting diodes.

Nature nanotechnology·2026
Same author

Aqueous Fe-Based Batteries: From Fe-Metal Anode Reversibility to Electrolyte Stabilization and Cathode Expansion.

ChemSusChem·2026
Same author

Physical Unclonable Function Based on 3D-NAND Flash Array Structure With Multi-Chip Implementation.

Small (Weinheim an der Bergstrasse, Germany)·2026

Related Experiment Video

Updated: Sep 20, 2025

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
08:07

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

8.0K

Intrinsic variation effect in memristive neural network with weight quantization.

Jinwoo Park1, Min Suk Song1, Sangwook Youn1

  • 1Department of Electronic Engineering, Inha University, Incheon 22212, Republic of Korea.

Nanotechnology
|June 7, 2022
PubMed
Summary

Intrinsic variations in memristor devices impact neuromorphic systems. This study quantifies these effects on neural network performance using a fabricated Al2O3/TiO2 memristor array and MNIST dataset.

Keywords:
intrinsic variationmemristive neural networkmemristor crossbar arrayneuromorphic systemoff-chip trainingweight quantization

More Related Videos

Stochastic Noise Application for the Assessment of Medial Vestibular Nucleus Neuron Sensitivity In Vitro
06:22

Stochastic Noise Application for the Assessment of Medial Vestibular Nucleus Neuron Sensitivity In Vitro

Published on: August 28, 2019

5.2K
Gradient Echo Quantum Memory in Warm Atomic Vapor
10:00

Gradient Echo Quantum Memory in Warm Atomic Vapor

Published on: November 11, 2013

12.9K

Related Experiment Videos

Last Updated: Sep 20, 2025

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
08:07

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

8.0K
Stochastic Noise Application for the Assessment of Medial Vestibular Nucleus Neuron Sensitivity In Vitro
06:22

Stochastic Noise Application for the Assessment of Medial Vestibular Nucleus Neuron Sensitivity In Vitro

Published on: August 28, 2019

5.2K
Gradient Echo Quantum Memory in Warm Atomic Vapor
10:00

Gradient Echo Quantum Memory in Warm Atomic Vapor

Published on: November 11, 2013

12.9K

Area of Science:

  • Materials Science
  • Neuroscience
  • Computer Engineering

Background:

  • Memristor devices are crucial for neuromorphic computing due to their analog memory capabilities.
  • Intrinsic device variations can significantly degrade the performance of memristive neural networks.
  • Understanding and quantifying these variations is essential for reliable neuromorphic system design.

Purpose of the Study:

  • To analyze the impact of intrinsic variations in Al2O3/TiO2-based memristors on neural network performance.
  • To implement and evaluate 3-bit multilevel conductance for weight quantization.
  • To assess the effects of tuning tolerance, random telegraph noise (RTN), and device yield on classification accuracy.

Main Methods:

  • Fabrication of a 32x32 Al2O3/TiO2 memristor crossbar array.
  • Implementation of 8-level weight quantization using memristor switching characteristics.
  • Off-chip training of a memristive neural network using the MNIST dataset.
  • Evaluation of classification accuracy under applied intrinsic variations (tuning tolerance, RTN, fault yield).

Main Results:

  • Successful implementation of 3-bit multilevel conductance with a tuning tolerance of ±4μA (±40μS).
  • Verified endurance and retention characteristics of the memristor devices.
  • Quantified the effect of intrinsic variations, including RTN, on the classification accuracy of the memristive neural network.
  • Demonstrated that intrinsic variations significantly influence the transfer of pre-trained weights.

Conclusions:

  • Intrinsic device variations are a critical factor affecting the performance of memristive neural networks.
  • The study provides a quantitative assessment of these variations, crucial for designing robust neuromorphic systems.
  • Consideration of measured intrinsic variations is essential when transferring pre-trained weights from off-chip training to memristive hardware.