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

Learning in Stochastic Bit Stream Neural Networks.

Max van Daalen1, John Shawe-Taylor, Jieyu Zhao

  • 1University of London, Egham, Surrey, TW20 0EX, UK

Neural Networks : the Official Journal of the International Neural Network Society
|August 1, 1996
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

From target specificity to metabolic efficiency: Design and optimization of etomidate analogues for potential improvement in postoperative outcomes.

Acta pharmaceutica Sinica. B·2026
Same author

The joint association of the combined triglyceride-glucose index and atherogenic index of plasma with hypertension on stroke risk across different glycemic status: a prospective cohort study.

Cardiovascular diabetology·2026
Same author

Peritoneal dialysis-associated peritonitis caused by Eikenella corrodens combined with Enterococcus avium: A case report and literature review.

Medicine·2026
Same author

STOML2 is not essential for spermatogenesis and male fertility in mice.

Biochemical and biophysical research communications·2026
Same author

Recent Advances in Chemical Probing Strategies for RNA Structure Determination In Vivo.

Chemistry (Weinheim an der Bergstrasse, Germany)·2026
Same author

Deep fine-grained clustering with model reusing.

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
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 new feedforward stochastic neural network with stochastic weights and bit stream data representation. This powerful model shows potential for real-world applications, including hardware implementation.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Traditional neural networks often rely on deterministic weights, limiting flexibility.
  • Implementing neural networks in hardware presents significant challenges.

Purpose of the Study:

  • To present novel learning techniques for a feedforward stochastic neural network.
  • To explore the potential of stochastic weights and bit stream data representation.
  • To demonstrate the model's applicability in hardware using standard digital VLSI technology.

Main Methods:

  • Developed a novel feedforward stochastic neural network architecture.
  • Utilized stochastic weights and a "bit stream" data representation.
  • Implemented and simulated learning techniques at three distinct levels, including on-chip learning.

Related Experiment Videos

Main Results:

  • The stochastic neural network demonstrated powerful performance on benchmark datasets.
  • Successfully applied the model to handwritten digit recognition tasks.
  • Validated the model's effectiveness for real-world applications.

Conclusions:

  • The proposed stochastic neural network offers a viable and powerful alternative for machine learning.
  • The model's design facilitates hardware implementation, paving the way for efficient digital VLSI applications.
  • The learning techniques presented are effective across multiple simulation levels.