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

Speeding up backpropagation using multiobjective evolutionary algorithms.

Hussein A Abbass1

  • 1Artificial Life and Adaptive Robotics Lab, School of Information Technology and Electrical Engineering, University of New South Wales, Australian Defence Force Academy, Canberra, ACT 2600, Australia. h.abbass@adfa.edu.au

Neural Computation
|October 28, 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

Machine teaching in Swarm Metaverse under different levels of autonomy.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2025
Same author

Swarm Metaverse for Multi-Level Autonomy Using Digital Twins.

Sensors (Basel, Switzerland)·2023
Same author

Characterization of Indicators for Adaptive Human-Swarm Teaming.

Frontiers in robotics and AI·2022
Same author

Assessing Human Judgment of Computationally Generated Swarming Behavior.

Frontiers in robotics and AI·2021
Same author

Weighted Gate Layer Autoencoders.

IEEE transactions on cybernetics·2021
Same author

The reliability and transparency bases of trust in human-swarm interaction: principles and implications.

Ergonomics·2020
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces a novel memetic Pareto artificial neural network algorithm that optimizes both training error and network architecture. This approach significantly reduces training time compared to traditional gradient-based methods for artificial neural networks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Training artificial neural networks (ANNs) using backpropagation is computationally intensive and time-consuming.
  • Optimizing ANN architecture alongside training parameters requires extensive experimentation and resources.

Purpose of the Study:

  • To present a novel optimization algorithm for training ANNs that reduces computational cost.
  • To introduce a method that simultaneously optimizes ANN architecture and minimizes training error.

Main Methods:

  • Developed a memetic Pareto artificial neural network algorithm combining a multiobjective evolutionary algorithm with gradient-based local search.
  • Implemented a self-adaptive version of the algorithm to further decrease computational demands.

Related Experiment Videos

Main Results:

  • The proposed memetic Pareto algorithm generates a set of optimized networks, balancing training error and architecture.
  • Empirical results demonstrate a significant reduction in training time compared to conventional gradient-based techniques.

Conclusions:

  • The memetic Pareto artificial neural network algorithm offers an efficient alternative for training ANNs.
  • This method effectively addresses the challenges of long training times and complex architecture optimization in ANNs.