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

Toward optimally distributed computation

P J Edwards1, A F Murray

  • 1Department of Electrical Engineering, Edinburgh University, UK.

Neural Computation
|June 6, 1998
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

Growth and population structure of Lodoicea maldivica in natural stands in Seychelles.

Plant biology (Stuttgart, Germany)·2024
Same author

Changes in germinability, ABA content and ABA embryonic sensitivity in developing seeds of Sorghum bicolor (L.) Moench. induced by water stress during grain filling.

The New phytologist·2021
Same author

Patterning of functional human astrocytes onto parylene-C/SiO<sub>2</sub> substrates for the study of Ca<sup>2+</sup> dynamics in astrocytic networks.

Journal of neural engineering·2018
Same author

Wound-induced changes in tomato leaves and their effects on the feeding patterns of larval lepidoptera.

Oecologia·2017
Same author

The effect of mollusc grazing on seedling recruitment in artificially created grassland gaps.

Oecologia·2017
Same author

Wound-induced changes in the palatability of Betula pubescens and B. pendula.

Oecologia·2017
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 optimal computation distribution in neural networks using weight saliency regularization. This method enhances fault tolerance and generalization in large networks, verified by simulations.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Feedforward neural networks often have uneven computation distribution.
  • This can impact fault tolerance and generalization in large architectures.

Purpose of the Study:

  • To introduce a method for optimally distributing computation in feedforward neural networks.
  • To enhance fault tolerance and generalization ability through regularization.

Main Methods:

  • Regularization of weight saliency to constrain parameter importance.
  • Constraining relative parameter importance for even computation distribution.

Main Results:

  • Simulation experiments verified theoretical predictions.

Related Experiment Videos

  • Demonstrated beneficial effects on fault-tolerance performance.
  • Showcased improvements in generalization ability.

    • Conclusions:

    • Regularization terms effectively distribute neural computation optimally.
    • The proposed method is beneficial for large network architectures.