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

Neural architecture design based on extreme learning machine.

Andrés Bueno-Crespo1, Pedro J García-Laencina, José-Luis Sancho-Gómez

  • 1Dpto. Informática de Sistemas, Universidad Católica San Antonio, Murcia, Spain.

Neural Networks : the Official Journal of the International Neural Network Society
|July 30, 2013
PubMed
Summary

This study introduces an efficient Extreme Learning Machine (ELM) method for designing MultiLayer Perceptron (MLP) neural network architectures. The technique optimizes classification by selecting relevant inputs and ensuring a unique, highly generalizable network design.

Related Concept Videos

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...
Neural Regulation01:37

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

A Multi-Source Sensor Dataset for Spain: Integrating Air Quality, Meteorological, Mobility and Calendar Records.

Sensors (Basel, Switzerland)·2026
Same author

Artificial intelligence for ovarian cancer diagnosis via ultrasound: a systematic review and quantitative assessment of model performance.

Frontiers in artificial intelligence·2025
Same author

Early-fusion hybrid CNN-transformer models for multiclass ovarian tumor ultrasound classification.

Frontiers in artificial intelligence·2025
Same author

Glaucoma detection: Binocular approach and clinical data in machine learning.

Artificial intelligence in medicine·2024
Same author

Biodegradation behaviour of pharmaceutical compounds and selected metabolites in activated sludge. A forecasting decision system approach.

Journal of environmental health science & engineering·2024
Same author

Author Correction: PAPILA: Dataset with fundus images and clinical data of both eyes of the same patient for glaucoma assessment.

Scientific data·2024

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Selecting optimal neural network architectures for pattern classification is complex.
  • Existing methods often incur high computational costs and lack unique solutions.
  • Identifying relevant input units, hidden neurons, and weights is crucial for effective classification.

Purpose of the Study:

  • To propose an efficient technique for designing MultiLayer Perceptron (MLP) architectures for classification.
  • To leverage the Extreme Learning Machine (ELM) algorithm for streamlined network design.
  • To achieve high generalization capability and a unique solution for MLP architecture selection.

Main Methods:

  • Utilizing the Extreme Learning Machine (ELM) algorithm for neural network architecture design.
Keywords:
Architecture designExtreme learning machineMultilayer perceptronNeural networks

Related Experiment Videos

  • Developing a novel technique for efficient MLP architecture selection.
  • Implementing a method that identifies and retains only relevant input connections for classification.

    • Main Results:

    • The proposed method efficiently designs MLP architectures for classification tasks.
    • The technique provides a unique solution for network architecture selection.
    • The resulting networks demonstrate high generalization capabilities.
    • Only relevant input connections are retained in the final network configuration.

    Conclusions:

    • The proposed ELM-based technique offers an efficient and effective solution for MLP architecture design in classification.
    • This approach overcomes the computational cost and uniqueness issues of traditional methods.
    • The method ensures that the final neural network is optimized by using only essential input features.