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

Protein Networks

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...

Protein Networks

Protein Networks

Biological Clocks and Seasonal Responses

Biological Clocks and Seasonal Responses

The circadian—or biological—clock is an intrinsic, timekeeping, molecular mechanism that allows plants to coordinate physiological activities over 24-hour cycles called circadian rhythms. Photoperiodism is a collective term for the biological responses of plants to variations in the relative lengths of dark and light periods. The period of light-exposure is called the photoperiod.

Network Covalent Solids

Network Covalent Solids

Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...

Simplified Synchronous Machine Model

Simplified Synchronous Machine Model

The Synchronous Machine Model is a fundamental tool in analyzing and ensuring the transient stability of power systems. This model simplifies the representation of a synchronous machine under balanced three-phase positive-sequence conditions, assuming constant excitation and ignoring losses and saturation. The model is pivotal for understanding the behavior of synchronous generators connected to a power grid, particularly during transient events.
In this model, each generator is connected to a...

Neural Regulation

Neural Regulation

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.

You might also read

Related Articles

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

Sort by

Same author

Salvianolic Acid B Attenuates Excitotoxic Neuronal Injury After Transient Cerebral Ischemia.

In vivo (Athens, Greece)·2026

Same author

Increased Risk of Heart Failure Among Stroke Survivors: A Nationwide Cohort Study.

Healthcare (Basel, Switzerland)·2026

Same author

TWIK-1 plays distinct roles in spinal and peripheral sensory circuits controlling mechanical sensitivity and neuropathic hypersensitivity.

Signal transduction and targeted therapy·2026

Same author

m<sup>6</sup>A-FORM: An m<sup>6</sup>A-focused Foundation Model for Decoding m<sup>6</sup>A Regulatory Function.

ArXiv·2026

Same author

Retinal Detachment Is Associated With Enhanced Correlated Firing and Oscillatory Activity.

Investigative ophthalmology & visual science·2026

Same author

Shared and Divergent Transcriptional Programs of Oligodendrocyte Differentiation Across Vertebrate Species Revealed by scRNA-seq Analysis.

International journal of molecular sciences·2026

Search research articles

Related Experiment Video

Updated: Jan 23, 2026

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Memristor Neural Network Training with Clock Synchronous Neuromorphic System.

Sumin Jo¹, Wookyung Sun², Bokyung Kim³

¹Department of Electronic and Electrical Engineering, Ewha Womans University, Seoul 03760, Korea. sumin5784@gmail.com.

|June 12, 2019

Summary

This study introduces a neuromorphic hardware system for memristor neural networks, enabling unsupervised learning via spike-timing-dependent plasticity. A novel "guide training" method facilitates supervised learning on nonlinear memristor devices for image classification.

Keywords:

Hebbian training guide training image classification memristor neuromorphic system

More Related Videos

A Method for Growing Bio-memristors from Slime Mold

A Method for Growing Bio-memristors from Slime Mold

Published on: November 2, 2017

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jan 23, 2026

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

A Method for Growing Bio-memristors from Slime Mold

A Method for Growing Bio-memristors from Slime Mold

Published on: November 2, 2017

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Neuromorphic engineering
Materials science

Background:

Memristor devices show promise for unsupervised learning, particularly spike-timing-dependent plasticity (STDP), in neuromorphic hardware.
The nonlinear characteristics of memristors pose challenges for traditional machine learning algorithms like backpropagation.

Purpose of the Study:

To design a neuromorphic hardware system for multilayer unsupervised learning using memristor neural networks.
To develop a novel training method, termed "guide training," for supervised learning on nonlinear memristor devices.
To demonstrate the feasibility of both unsupervised and supervised learning for image classification using the developed system.

Main Methods:

Designed a neuromorphic hardware system for multilayer unsupervised learning.
Implemented unsupervised learning using a memristor neural network, leveraging input-output correlations.
Devised "guide training," a supervised learning algorithm that updates synaptic weights using only input-output correlations, avoiding complex computations.
Conducted all training and inference simulations on the designed hardware system.

Main Results:

Successfully trained a nonlinear memristor neural network using unsupervised learning based on input-output correlations.
Demonstrated that the "guide training" method effectively trains nonlinear memristor devices in a supervised manner.
Achieved successful image classification using both Hebbian unsupervised training and guide supervised training methods on the memristor neural network.

Conclusions:

The designed neuromorphic hardware system and memristor neural network are suitable for implementing both unsupervised and supervised learning.
The "guide training" algorithm offers an effective and computationally efficient approach for training nonlinear memristor devices.
Memristor-based neuromorphic systems hold significant potential for advanced machine learning applications, including image classification.