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

Invariance and neural nets.

E Barnard1, D Casasent

  • 1Dept. of Electr. and Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA.

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

Consent and Chaperone Practices in Transvaginal Ultrasound: Exploring Sonographer Knowledge, Gender, and Ethical Challenges.

Irish medical journal·2026
Same author

Clinical, tactical and strategic benefits of a UK Spray Dried Plasma production capability.

BMJ military health·2025
Same author

Oral tranexamic acid as a preferred administration route for severe trauma in the extreme cold weather environment.

BMJ military health·2025
Same author

'Golden day' is a myth: rethinking medical timelines and risk in large scale combat operations.

BMJ military health·2024
Same author

Prehospital emergency care in a humanitarian environment: an overview of the ethical considerations.

BMJ military health·2023
Same author

Red cell haemolysis secondary to intraosseous (IO) blood transfusion in adult patients with major trauma: a systematic review.

BMJ military health·2023
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 an invariant-feature technique for neural network classifiers, enhancing pattern recognition. The method transforms feature spaces to achieve invariance, demonstrating good performance in a range imagery case study.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Neural networks are increasingly used for pattern recognition tasks.
  • Achieving invariance to transformations (e.g., rotation, scale) is crucial for robust pattern recognition.
  • Existing methods for achieving invariance in neural networks have limitations.

Purpose of the Study:

  • To explore techniques for achieving invariance in neural network classifiers.
  • To identify the most suitable technique for current neural network architectures.
  • To develop a general method for transforming feature spaces to be invariant to specified transformations.

Main Methods:

  • The study reviews various techniques for invariance in neural nets.
  • The invariant-feature technique is identified as most suitable.

Related Experiment Videos

  • A novel formulation of invariance using constraints on feature values is proposed.
  • A general method for feature space transformation is developed.

    • Main Results:

    • The invariant-feature technique is confirmed as highly suitable for neural classifiers.
    • The proposed method effectively transforms feature spaces for invariance.
    • The approach demonstrated good performance in a case study using range imagery.

    Conclusions:

    • The invariant-feature technique offers a promising approach for robust pattern recognition with neural networks.
    • The developed method provides a generalizable framework for achieving invariance.
    • This work contributes to the advancement of invariant pattern recognition using neural networks.