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

The target switch algorithm: a constructive learning procedure for feed-forward neural networks

C Campbell1, C P Vicente

  • 1Advanced Computing Research Centre, Bristol University, United Kingdom.

Neural Computation
|November 1, 1995
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

Analysis of primary care electronic health record data of people living with hepatitis B virus: infection and hepatocellular carcinoma risk associated with socio-economic deprivation.

Public health·2023
Same author

"Oh! How Modern! And... Are You Ok with That?": Consensually Non-Monogamous People's Experiences When Accessing Sexual Health Care.

Journal of sex research·2023
Same author

Whole-genome sequencing to investigate transmission of SARS-CoV-2 in the acute healthcare setting: a systematic review.

The Journal of hospital infection·2023
Same author

Guillain-Barré Syndrome and Unilateral Optic Neuritis Following Vaccination for COVID-19: A Case Report and Literature Review.

Neuro-ophthalmology (Aeolus Press)·2022
Same author

Overall survival in the OlympiA phase III trial of adjuvant olaparib in patients with germline pathogenic variants in BRCA1/2 and high-risk, early breast cancer.

Annals of oncology : official journal of the European Society for Medical Oncology·2022
Same author

Cutaneous adverse drug reactions to fixed-dose combination treatments for TB.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2022
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

We developed an efficient method to train feed-forward neural networks for binary classification tasks. This procedure also enables the creation of networks with binary-valued weights, suitable for hardware implementation and demonstrating strong generalization.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Science

Background:

  • Feed-forward neural networks are widely used for classification tasks.
  • Implementing neural networks in hardware can be challenging due to complexity.
  • Binary-valued weights offer potential for simplified hardware implementation.

Purpose of the Study:

  • To propose an efficient procedure for constructing and training feed-forward neural networks.
  • To demonstrate the applicability of this procedure for networks with binary-valued weights.
  • To highlight the potential benefits of binary-valued weight neural networks.

Main Methods:

  • Development of an efficient construction and training procedure for feed-forward neural networks.
  • Application of the procedure to binary classification problems with binary or analogue input data.

Related Experiment Videos

  • Adaptation of the procedure for generating neural networks with binary-valued weights.

    • Main Results:

    • The proposed procedure efficiently constructs and trains feed-forward neural networks.
    • The procedure successfully handles both binary and analogue input data for classification.
    • Feed-forward neural networks with binary-valued weights were successfully constructed.
    • These binary-weighted networks showed good generalization capabilities.

    Conclusions:

    • An efficient training procedure for feed-forward neural networks is presented.
    • The method facilitates the creation of binary-weighted neural networks.
    • Binary-weighted neural networks are promising for efficient hardware implementation and generalization.