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

Evolving efficient learning algorithms for binary mappings.

John A Bullinaria1

  • 1School of Computer Science, The University of Birmingham, Birmingham B15 2TT, UK.

Neural Networks : the Official Journal of the International Neural Network Society
|July 10, 2003
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

Simulating the Effect of Environmental Change on Evolving Populations.

Artificial life·2024
Same author

Effect of Environmental Change Distribution on Artificial Life Simulations.

Artificial life·2022
Same author

Imitative and Direct Learning as Interacting Factors in Life History Evolution.

Artificial life·2017
Same author

Limiting factors for mapping corpus-based semantic representations to brain activity.

PloS one·2013
Same author

Extracting semantic representations from word co-occurrence statistics: stop-lists, stemming, and SVD.

Behavior research methods·2012
Same author

Understanding the emergence of modularity in neural systems.

Cognitive science·2011
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

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

Decentralized ADMM for factorization-based Low-rank matrix estimation.

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

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

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

Q-learning based asynchronous Boolean control networks stabilization with data loss.

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

New results on prescribed-time synchronization of complex networks via intermittent control.

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

Variance-constrained multi-view ensemble broad network for imbalanced data.

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

Training sigmoidal neural networks for binary mappings can fail due to cost function issues. Simulated evolution identified the most efficient learning procedures for optimal binary mapping performance.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Gradient descent training of sigmoidal feed-forward neural networks often encounters issues with binary mappings.
  • A sum-squared-error cost function can cause weight updates to diminish as outputs approach maximal error, hindering learning.

Purpose of the Study:

  • To investigate and identify the most efficient learning procedures for training sigmoidal neural networks on binary mapping tasks.
  • To overcome common training pitfalls associated with gradient descent and sum-squared-error cost functions.

Main Methods:

  • Utilized simulated evolution to optimize all relevant parameters for neural network training.
  • Compared various common solutions including data modification, deviations from gradient descent, and cost function alterations.

Related Experiment Videos

Main Results:

  • Simulated evolution provided a clear conclusion on the most efficient approach for learning binary mappings.
  • Identified optimal parameter settings for effective training, addressing the limitations of standard gradient descent.

Conclusions:

  • Simulated evolution is an effective method for optimizing neural network training parameters.
  • Determined the most efficient strategy for sigmoidal feed-forward networks learning binary mappings, overcoming common gradient descent limitations.