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

Propagation of Action Potentials01:23

Propagation of Action Potentials

The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
Neuroplasticity01:01

Neuroplasticity

Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
Neural Circuits01:25

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

You might also read

Related Articles

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

Sort by
Same author

"Majority of the time, I know I'm right": understanding the decisions behind persistently high ED utilization among patients with substance use disorders.

BMC health services research·2025
Same author

Reducing Risks in Petrochemical Plants Through the Integration of Existing and Emerging Gas Leak Detection Technologies.

Sensors (Basel, Switzerland)·2025
Same author

Efficacy of the GLP-1 receptor agonist, semaglutide, in abstinence from illicit and nonprescribed opioids in an outpatient population with OUD: a randomized, double-blind, placebo-controlled clinical trial protocol.

Addiction science & clinical practice·2025
Same author

The intersection of aging, pain, and opioid use disorder: a retrospective chart review from an outpatient opioid treatment clinic.

Frontiers in pain research (Lausanne, Switzerland)·2025
Same author

Efficacy of the GLP-1 receptor agonist, semaglutide, in abstinence from illicit and nonprescribed opioids in an outpatient population with treatment-refractory OUD: A randomized, double-blind, placebo-controlled clinical trial protocol.

Research square·2025
Same author

Assessing Environment Resistance of the Korean Wild Boar ASFV Isolates "<i>ASFV/Yeoncheon/2019</i>".

Transboundary and emerging diseases·2025
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Videos

The No-Prop algorithm: a new learning algorithm for multilayer neural networks.

Bernard Widrow1, Aaron Greenblatt, Youngsik Kim

  • 1ISL, Department of Electrical Engineering, Stanford University, CA, USA. widrow@stanford.edu

Neural Networks : the Official Journal of the International Neural Network Society
|November 13, 2012
PubMed
Summary
This summary is machine-generated.

A novel No-Propagation (No-Prop) learning algorithm for neural networks fixes hidden layer weights, training only output layers. It offers faster convergence and simpler implementation than Back-Propagation, performing comparably when training data is within capacity.

Related Experiment Videos

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Multilayer neural networks are powerful tools for complex pattern recognition.
  • Traditional training algorithms like Back-Propagation can be computationally intensive.
  • Efficient training methods are crucial for advancing neural network applications.

Purpose of the Study:

  • Introduce a new learning algorithm, No-Propagation (No-Prop), for multilayer neural networks.
  • Examine the role of hidden layer nonlinearity using Least Mean Square Error Capacity (LMS Capacity).
  • Compare the performance of No-Prop with the established Back-Propagation algorithm.

Main Methods:

  • No-Prop algorithm: Fixes hidden-layer neuron weights randomly; trains only output-layer neuron weights.
  • Uses steepest descent and the Widrow-Hoff LMS algorithm to minimize mean square error.
  • Defines and analyzes Least Mean Square Error Capacity (LMS Capacity) as the maximum number of patterns trainable with zero error.

Main Results:

  • No-Prop's LMS Capacity equals the number of output-layer neuron weights.
  • No-Prop and Back-Prop show similar training and generalization performance when training patterns are within LMS Capacity.
  • Back-Prop generally outperforms No-Prop when training patterns exceed Capacity, though No-Prop can match performance by increasing hidden layer size.

Conclusions:

  • No-Prop is simpler, easier to implement, and converges faster than Back-Prop.
  • No-Prop offers comparable performance to Back-Prop under specific conditions (training data <= LMS Capacity).
  • Further research is needed to determine optimal use cases for No-Prop versus Back-Prop.