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

Heuristic pattern correction scheme using adaptively trained generalized regression neural networks.

T Hoya1, J A Chambers

  • 1Laboratory for Advanced Brain Signal Processing, BSI Riken, Wakoh-City, Saitama 351-0198 Japan. hoya@bsp.brain.riken.go.jp

IEEE Transactions on Neural Networks
|February 5, 2008
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

A regulatory phenotype associated with the en-am 1 mutant of Neurospora crassa.

Current genetics·2013
Same author

Trans-nuclear action of the nit-2 regulatory gene product and study of two additional nitrogen control genes in Neurospora crassa.

Current genetics·2013
Same author

An enhanced NAS-RIF algorithm for blind image deconvolution.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Toward an optimal PRNN-based nonlinear predictor.

IEEE transactions on neural networks·2008
Same author

On the choice of parameters of the cost function in nested modular RNN's.

IEEE transactions on neural networks·2008
Same author

On the capability of accommodating new classes within probabilistic neural networks.

IEEE transactions on neural networks·2008
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 heuristic pattern correction scheme for neural networks, enhancing incremental learning of misclassified patterns while maintaining past performance. The method uses adaptive generalized regression neural networks with growing and shrinking mechanisms.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Intelligent systems need to learn new patterns incrementally without forgetting past data.
  • Existing neural networks struggle with continuous learning and retaining performance on historical data.

Purpose of the Study:

  • To propose a heuristic pattern correction scheme for adaptive generalized regression neural networks (GRNNs).
  • To enable incremental learning of misclassified patterns while preserving performance on previously learned data.

Main Methods:

  • A network growing phase adds misclassified patterns iteratively until correct classification.
  • A dual-stage network shrinking phase removes redundancy, incorporating long- and short-term memory models.
  • The scheme utilizes adaptively trained generalized regression neural networks (GRNNs).

Related Experiment Videos

Main Results:

  • Extensive simulations demonstrate the learning capability of the proposed scheme.
  • The method effectively handles newly encountered misclassified patterns.
  • Maintained classification performance on previously stored patterns.

Conclusions:

  • The proposed heuristic pattern correction scheme offers an effective solution for incremental learning in neural networks.
  • The dual-stage shrinking mechanism, inspired by brain function, enhances learning efficiency.
  • This approach advances pattern classification by balancing new learning with memory retention.