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

Trial and Error and Algorithm01:12

Trial and Error and Algorithm

409
A problem-solving strategy is a plan of action used to find a solution. Different strategies have distinct action plans. Trial and error involves trying different solutions until one works. For instance, to fix a broken printer, you might check ink levels, ensure the paper tray isn't jammed, and verify the printer's connection to your laptop. This method can be time-consuming but is commonly used. Thomas Edison, for example, used trial and error to find a suitable filament for the light...
409
Systematic Error: Methodological and Sampling Errors01:15

Systematic Error: Methodological and Sampling Errors

11.0K
In the case of systematic errors, the sources can be identified, and the errors can be subsequently minimized by addressing these sources. According to the source, systematic errors can be divided into sampling, instrumental, methodological, and personal errors.
Sampling errors originate from improper sampling methods or the wrong sample population. These errors can be minimized by refining the sampling strategy. Defective instruments or faulty calibrations are the sources of instrumental...
11.0K
Fundamental Attribution Error01:14

Fundamental Attribution Error

13.8K
According to some social psychologists, people tend to overemphasize internal factors as explanations—or attributions—for the behavior of other people. They tend to assume that the behavior of another person is a trait of that person, and to underestimate the power of the situation on the behavior of others. They tend to fail to recognize when the behavior of another is due to situational variables, and thus to the person’s state. This erroneous assumption is...
13.8K
Random Error01:04

Random Error

9.8K
Random or indeterminate errors originate from various uncontrollable variables, such as variations in environmental conditions, instrument imperfections, or the inherent variability of the phenomena being measured. Usually, these errors cannot be predicted, estimated, or characterized because their direction and magnitude often vary in magnitude and direction even during consecutive measurements. As a result, they are difficult to eliminate. However, the aggregate effect of these errors can be...
9.8K
Margin of Error01:27

Margin of Error

7.6K
The margin of error is also called the maximum error of an estimate. The margin of error is the maximum possible or expected difference between the observed sample parameter value and the actual population parameter value. For proportion, it is the maximum difference between the value of sample proportion obtained from the data and the true value of population proportion. As the true value of the population parameter is not known, the margin of error is calculated using the sample statistic.
7.6K
Standard Error of the Mean01:13

Standard Error of the Mean

12.4K
The sampling variability of a statistic is defined as how much the statistic varies from one sample to another. The sampling variability of a statistic is typically measured by measuring its standard error.
The standard error of the mean is an example of a standard error. It is a unique standard deviation known as the standard deviation of the sampling distribution of the mean. The standard error of the mean is a statistic that calculates how correctly a sample distribution represents a...
12.4K

You might also read

Related Articles

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

Sort by
Same author

Measurement of the charge asymmetry in top quark pair production in <i>pp</i> collisions at [Formula: see text] using the ATLAS detector.

The European physical journal. C, Particles and fields·2015
Same author

Search for lepton flavour violation in the <i>eμ</i> continuum with the ATLAS detector in [Formula: see text]<i>pp</i> collisions at the LHC.

The European physical journal. C, Particles and fields·2015
Same author

Measurement of [Formula: see text] production with a veto on additional central jet activity in <i>pp</i> collisions at [Formula: see text] TeV using the ATLAS detector.

The European physical journal. C, Particles and fields·2015
Same author

Measurement of the top quark mass with the template method in the [Formula: see text] channel using ATLAS data.

The European physical journal. C, Particles and fields·2015
Same author

Search for heavy neutrinos and right-handed <i>W</i> bosons in events with two leptons and jets in <i>pp</i> collisions at [Formula: see text] with the ATLAS detector.

The European physical journal. C, Particles and fields·2015
Same author

Measurement of <i>τ</i> polarization in <i>W</i>→<i>τν</i> decays with the ATLAS detector in <i>pp</i> collisions at [Formula: see text].

The European physical journal. C, Particles and fields·2015
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Related Experiment Video

Updated: Feb 1, 2026

Genome-wide Surveillance of Transcription Errors in Eukaryotic Organisms
09:30

Genome-wide Surveillance of Transcription Errors in Eukaryotic Organisms

Published on: September 13, 2018

9.9K

Improving the error backpropagation algorithm with a modified error function.

S H Oh1

  • 1Res. Dept., Electron. and Telecommun. Res. Inst., Taejon.

IEEE Transactions on Neural Networks
|January 1, 1997
PubMed
Summary
This summary is machine-generated.

This study introduces a modified error function to speed up multilayer perceptron learning. The new method adjusts error signals to prevent output nodes from saturating, improving training efficiency for tasks like handwritten digit recognition.

More Related Videos

Rare Event Detection Using Error-corrected DNA and RNA Sequencing
10:36

Rare Event Detection Using Error-corrected DNA and RNA Sequencing

Published on: August 3, 2018

12.6K
Errors as a Means of Reducing Impulsive Food Choice
07:07

Errors as a Means of Reducing Impulsive Food Choice

Published on: June 5, 2016

9.2K

Related Experiment Videos

Last Updated: Feb 1, 2026

Genome-wide Surveillance of Transcription Errors in Eukaryotic Organisms
09:30

Genome-wide Surveillance of Transcription Errors in Eukaryotic Organisms

Published on: September 13, 2018

9.9K
Rare Event Detection Using Error-corrected DNA and RNA Sequencing
10:36

Rare Event Detection Using Error-corrected DNA and RNA Sequencing

Published on: August 3, 2018

12.6K
Errors as a Means of Reducing Impulsive Food Choice
07:07

Errors as a Means of Reducing Impulsive Food Choice

Published on: June 5, 2016

9.2K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • The error backpropagation (EBP) algorithm is fundamental for training multilayer perceptrons (MLPs).
  • MLPs often face slow learning speeds due to issues with the EBP algorithm.
  • Sigmoid activation functions can lead to saturated output nodes, hindering effective learning.

Purpose of the Study:

  • To accelerate the learning speed of the EBP algorithm for MLPs.
  • To mitigate the problem of slow convergence in neural network training.
  • To enhance the performance of MLPs by modifying the error function.

Main Methods:

  • A modified error function is proposed to improve the EBP algorithm.
  • The method adjusts error signals to reduce the likelihood of output nodes reaching extreme values of the sigmoid function.
  • Stronger error signals are applied to incorrectly saturated nodes, while weaker signals are used for correctly saturated nodes.

Main Results:

  • The proposed method effectively accelerates the learning speed of MLPs.
  • It prevents output nodes from incorrectly saturating, leading to more efficient training.
  • A reduction in overspecialization for training patterns was observed due to the weak error signal for correctly saturated nodes.
  • Demonstrated effectiveness in a handwritten digit recognition task.

Conclusions:

  • The modified error function offers a significant improvement over the standard EBP algorithm.
  • This approach enhances MLP training efficiency and robustness.
  • The method shows promise for practical applications, including pattern recognition.