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

Anticipation-based temporal sequences learning in hierarchical structure.

Janusz A Starzyk1, Haibo He

  • 1School of Electrical Engineering and Computer Science, Ohio University, Athens, OH 45701, USA. starzyk@bobcat.ent.ohiou.edu

IEEE Transactions on Neural Networks
|March 28, 2007
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

WormSORT: A detection-based multiple object tracking model for individual silkworms in breeding environments.

PLoS computational biology·2026
Same author

Research progress on chemical metabolites, processing technologies, and pharmacological activities of asperosaponin VI: a systematic review and critical evaluation.

Frontiers in pharmacology·2026
Same author

Artificial intelligence-assisted detection of epileptic spasms using electroencephalographic-video analysis.

Epilepsia·2026
Same author

Epidemiological characteristics and incidence prediction analysis of brucellosis in Bayingolin mongol autonomous prefecture, Xinjiang.

BMC infectious diseases·2026
Same author

Patient satisfaction and its influencing factors: results from a survey in inpatient department in a tertiary hospital setting in China.

BMC health services research·2026
Same author

Ecological regime shifts weaken sedimentary carbon sequestration in shallow Lake liangzi.

Water research·2025
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 hierarchical model for complex temporal sequence learning, enhancing artificial intelligence capabilities. The model uses prediction and one-shot learning for efficient sequence recognition and adaptation.

Area of Science:

  • Artificial Intelligence
  • Cognitive Science
  • Computational Neuroscience

Background:

  • Temporal sequence learning is fundamental to human intelligence.
  • Existing models often struggle with complex, hierarchical temporal data.
  • Need for efficient learning mechanisms that adapt quickly.

Purpose of the Study:

  • To propose a novel hierarchical structure for complex temporal sequence learning.
  • To integrate prediction and one-shot learning for enhanced performance.
  • To demonstrate the model's capability in recognizing sequences at multiple levels.

Main Methods:

  • A hierarchical model with four levels: letters, words, sentences, and strophes.
  • Modified Hebbian learning for pattern recognition at the base level.

Related Experiment Videos

  • Winner-take-all (WTA) mechanism for neuron selection and hierarchical input.
  • Integration of a prediction mechanism with one-shot learning for adaptation.

    • Main Results:

    • The model successfully learns and predicts temporal sequences across different hierarchical levels.
    • Correct predictions indicate sequence mastery, reducing the need for further learning.
    • Incorrect predictions trigger one-shot learning, enabling rapid adaptation to new sequences.
    • Demonstrated effectiveness using a four-level hierarchy (letters, words, sentences, strophes).

    Conclusions:

    • The proposed hierarchical model offers a robust framework for complex temporal sequence learning.
    • The combination of prediction and one-shot learning facilitates efficient and adaptive sequence recognition.
    • This approach advances artificial intelligence by mimicking critical aspects of human temporal processing.