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

Optimal training of thresholded linear correlation classifiers.

T H Hildebrandt1

  • 1Dept. of Electr. and Comput. Eng., North Carolina State Univ., Raleigh, NC.

IEEE Transactions on Neural Networks
|January 1, 1991
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

Comments on ;Optimal training of thresholded linear correlation classifiers' [with reply].

IEEE transactions on neural networks·1993
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 closed-form solution for faster pattern recognition, significantly reducing training time to a single epoch. This method also demonstrates superior generalization capabilities compared to other models.

Area of Science:

  • Computer Science
  • Machine Learning
  • Artificial Intelligence

Background:

  • Pattern recognition is crucial in various AI applications.
  • Current methods often require extensive training time and computational resources.
  • Improving efficiency and generalization in pattern recognition remains a key challenge.

Purpose of the Study:

  • To present a novel closed-form solution for pattern recognition.
  • To reduce the training time to a single epoch.
  • To compare the generalization performance against existing models.

Main Methods:

  • Development of a closed-form solution for pattern recognition.
  • Analysis of hardware requirements for the proposed method.
  • Comparative analysis of generalization capabilities.

Related Experiment Videos

Main Results:

  • The proposed closed-form solution achieves training in a single epoch.
  • Hardware requirements are comparable to regular recognition under specific conditions.
  • The closed-form method shows superior generalization compared to models with diagonal transformations only.

Conclusions:

  • The presented closed-form solution offers a significant improvement in training efficiency for pattern recognition.
  • The method is computationally feasible and demonstrates enhanced generalization.
  • This approach has the potential to advance AI applications requiring rapid and accurate pattern recognition.