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

A new on-line learning model.

S Mendelson1

  • 1Department of Mathematics, Technion, Haifa 32000, Israel.

Neural Computation
|March 20, 2001
PubMed
Summary
This summary is machine-generated.

We present a novel supervised learning model based on nonhomogeneous Markov processes. This model guarantees convergence to a correct state, ensuring agreement with the teacher, with applications in neural network learning rules.

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

Concordance between epidemiological evaluation of probability of transmission and whole genome sequence relatedness among hospitalized patients acquiring Klebsiella pneumoniae carbapenemase-producing Klebsiella pneumoniae.

Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases·2020
Same author

Diet restriction in mice causes a decrease in hippocampal choline uptake and muscarinic receptors that is restored by administration of tyrosine: interaction between cholinergic and adrenergic receptors influencing cognitive function.

Nutritional neuroscience·2002
Same author

Tyrosine improves appetite, cognition, and exercise tolerance in activity anorexia.

Medicine and science in sports and exercise·2001
Same author

Recurrence methods in the analysis of learning processes.

Neural computation·2001
Same author

[Ionizing irradiation for the prevention of coronary and peripheral artery restenosis].

Harefuah·2000
Same author

In-vivo strain measurements to evaluate the strengthening potential of exercises on the tibial bone.

The Journal of bone and joint surgery. British volume·2000
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

Area of Science:

  • Machine Learning
  • Probability Theory
  • Computational Neuroscience

Background:

  • Supervised learning models are crucial for artificial intelligence.
  • Understanding convergence properties is key to reliable learning.
  • Markov processes offer a framework for modeling sequential learning.

Purpose of the Study:

  • Introduce a new supervised learning model.
  • Investigate the convergence properties of this model.
  • Establish conditions for reaching a 'correct state' where the system matches the teacher's output.

Main Methods:

  • Formulate a nonhomogeneous Markov process for supervised learning.
  • Develop and prove a sufficient condition for almost sure convergence.
  • Apply the convergence theorem to analyze existing neural network learning rules.

Related Experiment Videos

Main Results:

  • A novel nonhomogeneous Markov process model for supervised learning is introduced.
  • A sufficient condition for the model to converge to a correct state is proven.
  • Convergence results are demonstrated for established learning rules in neural networks.

Conclusions:

  • The proposed model provides a theoretical foundation for supervised learning convergence.
  • The findings offer insights into the behavior of neural network learning rules.
  • This work contributes to the understanding of learning dynamics in artificial systems.