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

A high performance k-NN approach using binary neural networks.

Victoria J Hodge1, Ken J Lees, James L Austin

  • 1Advanced Computer Architecture Group, Department of Computer Science, University of York, Heslington, York YO10 5DD, UK. vicky@cs.york.ac.uk

Neural Networks : the Official Journal of the International Neural Network Society
|March 24, 2004
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

Cautious optimism: public voices on medical AI and sociotechnical harm.

Frontiers in digital health·2025
Same author

Real-time 3D tracking of swimming microbes using digital holographic microscopy and deep learning.

PloS one·2024
Same author

Medical practitioner perspectives on AI in emergency triage.

Frontiers in digital health·2023
Same author

On the use of AI for Generation of Functional Music to Improve Mental Health.

Frontiers in artificial intelligence·2021
Same author

Hadoop neural network for parallel and distributed feature selection.

Neural networks : the official journal of the International Neural Network Society·2015
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
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

This study introduces a novel binary neural network k-nearest neighbour (k-NN) classifier. This innovative approach significantly enhances data classification speed and reduces memory usage compared to conventional methods.

Area of Science:

  • Computer Science
  • Machine Learning
  • Artificial Intelligence

Background:

  • K-nearest neighbour (k-NN) algorithms are widely used for classification.
  • Traditional k-NN methods can be computationally intensive and memory-demanding for large datasets.
  • Binary neural networks offer potential for efficient data processing.

Purpose of the Study:

  • To evaluate a novel k-nearest neighbour (k-NN) classifier integrated with binary neural networks.
  • To assess the performance of this binary approach against conventional k-NN methods.
  • To identify optimal configurations for the binary k-NN classifier.

Main Methods:

  • Developing a binary neural network classifier using robust encoding for diverse data types (ordinal, categorical, numeric).

Related Experiment Videos

  • Implementing high-speed pattern matching within the binary neural network to retrieve candidate records.
  • Applying a conventional k-NN approach to the candidate set for final k-best match determination.
  • Comparing memory overheads, training speed, retrieval speed, and retrieval accuracy of the binary and conventional approaches.

    • Main Results:

    • The binary neural network k-NN classifier demonstrated superior performance in terms of speed.
    • Significant reductions in memory requirements were observed with the binary approach.
    • Various configurations of the binary approach were tested, and optimal settings were identified.

    Conclusions:

    • The novel binary neural network k-NN classifier offers a more efficient alternative to conventional k-NN methods.
    • This approach provides substantial improvements in both computational speed and memory efficiency.
    • The findings highlight the potential of binary neural networks for accelerating k-NN classification tasks.