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

High-capacity Hebbian storage by sparse sampling.

D Sal'ee1, Y Baram

  • 1Department of Defence.

IEEE Transactions on Neural Networks
|January 1, 1995
PubMed
Summary
This summary is machine-generated.

This study reveals that networks of ternary neurons can store significantly more information than previously thought. These findings advance the understanding of neural network capacity and error correction capabilities.

Related Experiment Videos

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

Effects of cisplatin on olfactory function in cancer patients.

British journal of cancer·2005
Same author

Random embedding machines for pattern recognition.

Neural computation·2001
Same author

Manifold stochastic dynamics for Bayesian learning.

Neural computation·2001
Same author

Multidimensional density shaping by sigmoids.

IEEE transactions on neural networks·1996
Same author

[Primary CNS lymphoma--new aspects in diagnosis and treatment].

Harefuah·1995
Same author

Second-order bounds on the domain of attraction and the rate of convergence of nonlinear dynamical systems and neural networks.

IEEE transactions on neural networks·1994
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

Area of Science:

  • Computational neuroscience
  • Machine learning theory
  • Information theory

Background:

  • Artificial neural networks (ANNs) are crucial for machine learning.
  • Understanding the storage capacity of ANNs is fundamental.
  • Previous research focused primarily on binary neurons.

Purpose of the Study:

  • To determine the storage capacity of ternary neural networks.
  • To analyze the error correction capabilities of these networks.
  • To generalize existing capacity bounds for binary networks.

Main Methods:

  • Mathematical analysis of Hebbian learning rule in ternary networks.
  • Derivation of capacity bounds for sparse ternary vectors.
  • Comparison with capacity bounds of binary networks.

Main Results:

  • The capacity of ternary networks is at least of the order of N(2)/K log N.
  • Error correction capabilities were analyzed for these networks.
  • Higher capacities are achieved for small values of K compared to binary networks.

Conclusions:

  • Ternary neural networks offer enhanced storage capacity.
  • The findings generalize and improve upon existing neural network capacity theories.
  • Sparse ternary representations are efficient for information storage.