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 and generation of long-range correlated sequences

Priel1, Kanter

  • 1Minerva Center and Department of Physics, Bar-Ilan University, 52900 Ramat-Gan, Israel.

Physical Review. E, Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics
|November 23, 2000
PubMed
Summary

This study shows that neural networks can learn and generate long-range, power-law correlated sequences. The network

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

Cascading parity-check error-correcting codes

Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics·2000
Same author

Emergence of Chaos in Asymmetric Networks.

Physical review letters·1996
Same author

Ionization and fragmentation of C60 by highly charged, high-energy xenon ions.

Physical review. A, Atomic, molecular, and optical physics·1996
Same author

Experimental determination of nondipolar angular distribution parameters for photoionization in the Ar K and Kr L shells.

Physical review. A, Atomic, molecular, and optical physics·1996
Same author

Mean-field behavior of cluster dynamics.

Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics·1996
Same author

Fully Differential Cross Sections for Double Photoionization of He Measured by Recoil Ion Momentum Spectroscopy.

Physical review letters·1996

Area of Science:

  • Computational neuroscience
  • Machine learning theory

Background:

  • Neural networks are increasingly used for sequence analysis.
  • Understanding their ability to capture complex statistical properties is crucial.

Purpose of the Study:

  • To investigate if fully connected asymmetric networks can learn and generate power-law correlated sequences.
  • To explore how neural networks extract statistical features from data.

Main Methods:

  • Training a fully connected asymmetric network on sequences.
  • Analyzing the statistical properties of generated sequences.
  • Examining the correlation structure within the network's weight matrix.

Main Results:

  • The trained network successfully learned the average power-law behavior.
  • Generated sequences exhibited similar statistical properties to the training data.
  • A correlated weight matrix with power-law characteristics induced similar sequence behavior.

Conclusions:

  • Fully connected asymmetric networks are capable of learning and generating power-law correlated sequences.
  • The network's ability to extract statistical features is demonstrated.
  • Weight matrix correlations play a key role in generating sequences with specific statistical behaviors.

Related Experiment Videos