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

Recurrence methods in the analysis of learning processes.

S Mendelson1, I Nelken

  • 1Department of Mathematics, Technion, and Institute of Computer Science, Hebrew University, Jerusalem 91120, Israel.

Neural Computation
|August 17, 2001
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

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

Ultra-fine frequency tuning revealed in single neurons of human auditory cortex.

Nature·2008
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

Sound-localization experiments with barn owls in virtual space: influence of interaural time difference on head-turning behavior.

Journal of the Association for Research in Otolaryngology : JARO·2001
Same author

Auditory edge detection: a neural model for physiological and psychoacoustical responses to amplitude transients.

Journal of neurophysiology·2001
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

We developed an easy-to-verify condition to ensure machine learning processes reach target states reliably. This method guarantees infinite visits to correct states, applicable to various learning rules.

Area of Science:

  • Machine Learning
  • Computational Theory
  • Artificial Intelligence

Background:

  • The primary objective of machine learning is to guide systems toward desired 'correct' states.
  • Verifying that learning processes consistently reach these target states can be practically challenging.

Purpose of the Study:

  • To introduce a novel, verifiable condition that guarantees a learning process will infinitely often visit the target set.
  • To demonstrate the broad applicability and utility of this condition across diverse machine learning algorithms.

Main Methods:

  • Presentation of a new theoretical condition for ensuring target set convergence in learning processes.
  • Verification of the condition's ease of application and its prevalence in established learning rules.
  • Empirical validation through application to the perceptron, energy-function-based rules, Kohonen rule, and committee machines.

Related Experiment Videos

Main Results:

  • The proposed condition reliably ensures that the learning process visits the target set infinitely often with almost sure probability.
  • The condition is demonstrated to be straightforward to verify for a range of common machine learning algorithms.
  • Successful application across four distinct learning paradigms validates the method's versatility.

Conclusions:

  • The presented condition offers a robust and practical solution for verifying convergence in machine learning.
  • This work provides a valuable theoretical tool for analyzing and guaranteeing the performance of learning systems.
  • The findings are broadly applicable, enhancing confidence in the reliability of various machine learning approaches.