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

Training a network with ternary weights using the CHIR algorithm.

S Abramson1, D Saad, E Marom

  • 1Fac. of Eng., Tel Aviv Univ.

IEEE Transactions on Neural Networks
|January 1, 1993
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

Artificial Intelligence Clustering Approach for Force Mapping Analysis of Polyacrylic Acid (PAA)/Polyethylene Oxide (PEO) Polymer Brushes for Biosensor Applications.

Journal of molecular recognition : JMR·2026
Same author

Potential diagnostic value of a type X collagen neo-epitope biomarker for knee osteoarthritis.

Osteoarthritis and cartilage·2019
Same author

Communication networks beyond the capacity crunch.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2016
Same author

Disseminated histoplasmosis in allogeneic bone marrow transplant: a diagnosis not to be missed.

Transplant infectious disease : an official journal of the Transplantation Society·2014
Same author

The coupling of bone and cartilage turnover in osteoarthritis: opportunities for bone antiresorptives and anabolics as potential treatments?

Annals of the rheumatic diseases·2013
Same author

Vascular and upper gastrointestinal effects of non-steroidal anti-inflammatory drugs: meta-analyses of individual participant data from randomised trials.

Lancet (London, England)·2013
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

A modified binary weight CHIR algorithm introduces a zero state, enabling solutions with reduced network connectivity. This enhancement maintains similar convergence rates while expanding solvable problems without extra parameters.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • The binary weight CHIR algorithm is a computational model for neural networks.
  • Existing binary weight networks have limitations in connectivity and problem scope.

Purpose of the Study:

  • To introduce a modified binary weight CHIR algorithm with an added zero state.
  • To explore the impact of this modification on network connectivity and problem-solving capabilities.

Main Methods:

  • A modification of the binary weight CHIR algorithm was developed, incorporating a zero state.
  • Extensive computer simulations were conducted on parity, symmetry, and teacher problems.

Main Results:

  • The modified algorithm achieves solutions with reduced network connectivity.

Related Experiment Videos

  • Convergence rates comparable to the binary CHIR2 algorithm were observed.
  • The set of solvable problems for binary weight networks was expanded.

    • Conclusions:

    • The addition of a zero state to the binary weight CHIR algorithm offers a more flexible and efficient network configuration.
    • This modification enhances problem-solving capacity without increasing complexity or parameter requirements.