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 Experiment Videos

Data classification with multilayer perceptrons using a generalized error function.

Luís M Silva1, J Marques de Sá, Luís A Alexandre

  • 1INEB-Instituto de Engenharia Biomédica, Porto, Portugal. Imsilva@fe.up.pt

Neural Networks : the Official Journal of the International Neural Network Society
|June 24, 2008
PubMed
Summary
This summary is machine-generated.

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

Twelve years of genomic surveillance of vancomycin-resistant Enterococcus faecium: emergence of linear vanA and bacteriocin-carrying plasmids challenging infection control.

Genome medicine·2026
Same author

Authors' Reply to 'Methodological Considerations for Surveys of Dental Students' Knowledge and Attitudes Towards Artificial Intelligence in Oral Cancer Diagnosis'.

Oral diseases·2026
Same author

Knowledge, Attitudes, and Perceptions of Evidence-Based Dentistry Among Final-Year Dental Students: A Multinational Study Across 6 Countries and 8 Universities.

European journal of dental education : official journal of the Association for Dental Education in Europe·2026
Same author

Testing the redox theory of aging under parasitism.

npj aging·2026
Same author

Integrating the Microbiome Into Infection Ecology and Evolution in Wild Animals.

Molecular ecology·2026
Same author

Dental Students' Knowledge, Attitudes and Perceptions of Artificial Intelligence Tools to Aid in the Diagnosis of Oral Cancer and Oral Potentially Malignant Disorders.

Oral diseases·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
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

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

A new generalized error function, E(Exp), for multilayer perceptron learning optimizes performance by emulating other error functions through parameter adjustment. This flexible approach improves results in data classification tasks.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Neural Networks

Background:

  • Multilayer perceptron (MLP) learning relies on optimizing error functions to minimize the difference between predicted and target outputs.
  • Existing error functions possess distinct mathematical properties influencing their effectiveness in data classification.

Purpose of the Study:

  • To introduce and analyze a novel, generalized error function, E(Exp), for MLP networks.
  • To demonstrate E(Exp)'s ability to emulate various existing error functions via parameter tuning.
  • To evaluate E(Exp)'s performance and flexibility in data classification tasks.

Main Methods:

  • Review and mathematical analysis of common MLP error functions.
  • Introduction of the E(Exp) error function, inspired by the Z-EDM algorithm.

Related Experiment Videos

  • Experimental evaluation of E(Exp) against traditional error functions on classification problems.

    • Main Results:

    • The proposed E(Exp) function exhibits a generalized behavior, capable of mimicking other error functions.
    • Adjusting a single parameter in E(Exp) allows for emulation of diverse error function characteristics.
    • Experimental results indicate that E(Exp) achieves optimal performance comparable to specialized functions, with performance improvements in certain cases.

    Conclusions:

    • The E(Exp) error function offers enhanced flexibility and adaptability for MLP training.
    • Its generalized nature simplifies the selection of appropriate error functions for classification.
    • E(Exp) represents a significant advancement in optimizing neural network learning processes.