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

Incremental learning of complex temporal patterns.

D L Wang1, B Yuwono

  • 1Lab. for Artificial Intelligence Res., Ohio State Univ., Columbus, OH.

IEEE Transactions on Neural Networks
|January 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

[Effects of lipopolysaccharide-activated interferon gene stimulator signaling on periodontal ligament cells].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2025
Same author

[Some thoughts on the research of mesenchymal stem cell exosomes and wound microenvironment].

Zhonghua shao shang yu chuang mian xiu fu za zhi·2023
Same author

[Plasmids carried by carbapenems-resistant <i>Klebsiella pneumoniae</i> in burn patients and its correlation with strain transmission].

Zhonghua shao shang yu chuang mian xiu fu za zhi·2023
Same author

[Clinical application effects of two longitudes three transverses method in perforator location of thoracodorsal artery perforator flap and deep wound repair].

Zhonghua shao shang yu chuang mian xiu fu za zhi·2022
Same author

[Research advances on the roles of exosomes derived from mesenchymal stem cells in wound healing and prevention and treatment of hypertrophic scars].

Zhonghua shao shang za zhi = Zhonghua shaoshang zazhi = Chinese journal of burns·2021
Same author

Intrinsical localization of both topological (anti-kink) envelope and gray (black) gap solitons of the condensed bosons in deep optical lattices.

Chaos (Woodbury, N.Y.)·2020
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 neural model for sequential learning, demonstrating its capacity for incremental learning of complex patterns. A novel chunking mechanism significantly reduces interference, enhancing its effectiveness as a sequential memory.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Machine Learning

Background:

  • Neural networks are explored for temporal pattern generation.
  • Sequential learning presents challenges like interference when acquiring new data.

Purpose of the Study:

  • To analyze a neural model's ability to learn multiple complex sequences incrementally.
  • To investigate the impact of interference during sequential training.
  • To evaluate the effectiveness of a chunking mechanism in improving sequential memory.

Main Methods:

  • A neural model was trained sequentially with complex temporal patterns.
  • The model's performance was evaluated with highly correlated sequences.
  • A chunking network was integrated to detect and utilize repeated subsequences.

Related Experiment Videos

Main Results:

  • The model demonstrated incremental learning of a finite set of complex sequences.
  • Sequence integrity increased linearly with prior learning, with interference being memory-size independent.
  • The chunking mechanism substantially reduced retraining needs during sequential training.

Conclusions:

  • The neural model, especially with the chunking extension, functions as an effective sequential memory.
  • The chunking mechanism mitigates interference, enabling more efficient incremental learning.
  • The findings contribute to understanding and developing robust artificial sequential memory systems.