Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Efficacy, safety, and immunogenicity of an Escherichia coli-produced nine-valent human papillomavirus vaccine: a multicentre, double-blind, randomised, controlled, phase 3 trial.

The Lancet. Infectious diseases·2026

Same author

FCGR2B drives immunosuppressive M2 polarization of tumor-associated macrophages via metabolic reprogramming of fatty acid oxidation.

Cell cycle (Georgetown, Tex.)·2026

Same author

Inducible CRISPRi enables efficient and high-fidelity genome editing in Streptomyces.

Nucleic acids research·2026

Same author

Letter to the editor regarding "Romosozumab versus teriparatide and risk of all-cause mortality in patients with osteoporosis: a real-world propensity score-matched cohort study".

Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA·2026

Same author

Preparation and Anodic Bonding Performance of (PEG)<sub>10</sub>LiClO<sub>4</sub>/NaAlOSiO Solid Electrolyte for Packaging.

International journal of molecular sciences·2026

Same author

Novel immunomodulatory peptides identified from Mytilus edulis: Molecular docking, immunomodulatory effects on RAW264.7 cells and molecular dynamics simulation studies.

International immunopharmacology·2026

Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026

Same journal

Self-Supervised Continuous Dynamic Graph Representation Learning via Hawkes Processes.

IEEE transactions on neural networks and learning systems·2026

Same journal

cPU: Consistent Risk Estimator for Positive-Unlabeled Learning.

IEEE transactions on neural networks and learning systems·2026

Same journal

Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing.

IEEE transactions on neural networks and learning systems·2026

Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Mar 31, 2026

A Method for Growing Bio-memristors from Slime Mold

A Method for Growing Bio-memristors from Slime Mold

Published on: November 2, 2017

Feature Extraction Using Memristor Networks.

Patrick M Sheridan, Chao Du, Wei D Lu

IEEE Transactions on Neural Networks and Learning Systems

|October 30, 2015

Summary

This summary is machine-generated.

Memristor crossbar arrays enable efficient sparse coding for natural images. This technology achieves high sparsity and robustness against device variations, comparable to software methods.

More Related Videos

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

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

Published on: March 9, 2019

Design, Surface Treatment, Cellular Plating, and Culturing of Modular Neuronal Networks Composed of Functionally Inter-connected Circuits

Design, Surface Treatment, Cellular Plating, and Culturing of Modular Neuronal Networks Composed of Functionally Inter-connected Circuits

Published on: April 15, 2015

Related Experiment Videos

Last Updated: Mar 31, 2026

A Method for Growing Bio-memristors from Slime Mold

A Method for Growing Bio-memristors from Slime Mold

Published on: November 2, 2017

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

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

Published on: March 9, 2019

Design, Surface Treatment, Cellular Plating, and Culturing of Modular Neuronal Networks Composed of Functionally Inter-connected Circuits

Design, Surface Treatment, Cellular Plating, and Culturing of Modular Neuronal Networks Composed of Functionally Inter-connected Circuits

Published on: April 15, 2015

Area of Science:

Neuromorphic Engineering
Computational Neuroscience
Image Processing

Background:

Dictionary learning and sparse coding are crucial for efficient data representation.
Memristive crossbar arrays offer a promising hardware platform for neural computation.
Implementing complex algorithms like sparse coding on hardware faces challenges due to device variability.

Purpose of the Study:

To investigate the feasibility of using memristor crossbar arrays for dictionary learning and sparse coding of natural images.
To evaluate the impact of device nonlinearity and parameter variations on the performance of sparse coding.
To propose a compensation method for enhancing the robustness of memristor-based sparse coding.

Main Methods:

Utilized a winner-take-all training algorithm with Oja's rule to learn an overcomplete dictionary of Gabor-like features.
Employed the locally competitive algorithm for sparse representation of input images using the learned dictionary.
Assessed the effects of device nonlinearity and parameter variations on sparsification accuracy.
Developed and applied a compensation procedure to mitigate performance degradation.

Main Results:

The memristor crossbar architecture successfully learned feature primitives resembling Gabor filters.
Sparse representations of natural images were effectively generated.
Device nonlinearity and variations up to 100% were evaluated.
A compensation procedure significantly improved robustness against device variations.

Conclusions:

Memristor crossbar arrays are capable of performing dictionary learning and sparse coding for natural images.
The proposed compensation method ensures robust performance even with substantial device-to-device variations.
This hardware approach offers a viable alternative to software implementations for sparse coding, achieving comparable distortion at high sparsity.