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

Memorizing binary vector sequences by a sparsely encoded network.

Y Baram1

  • 1Dept. of Comput. Sci., Technion-Israel Inst. of Technol., Haifa.

IEEE Transactions on Neural Networks
|January 1, 1994
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

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

High-capacity Hebbian storage by sparse sampling.

IEEE transactions on neural networks·1995
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

This study introduces a novel neural network for memorizing and correcting binary vector sequences using Hebbian learning and sparse coding. The network demonstrates improved error correction through lateral connections and transmission delays.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Machine Learning

Background:

  • Traditional neural networks face challenges in robust sequence memorization and error correction.
  • Hebbian learning and sparse coding offer potential for efficient information storage.

Purpose of the Study:

  • To develop a neural network capable of memorizing and correcting sequences of binary vectors.
  • To investigate the impact of network architecture and parameters on performance.

Main Methods:

  • Implementation of a neural network utilizing Hebbian storage and sparse internal coding.
  • Employing a ternary Kanerva memory in a feedback configuration.
  • Introducing lateral connections and varying transmission delays between network layers.

Related Experiment Videos

Main Results:

  • The network successfully memorized and regenerated binary vector sequences.
  • Lateral connections significantly increased network capacity and error correction ability.
  • Higher transmission delays further enhanced the network's capability to correct input pattern errors.

Conclusions:

  • The proposed neural network architecture effectively handles sequence memorization and correction.
  • Hebbian learning, sparse coding, and specific architectural modifications (lateral connections, delays) are crucial for robust performance.
  • This model shows promise for applications requiring reliable pattern recognition and data recovery.