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

Canonical piecewise-linear networks.

J N Lin1, R Unbehauen

  • 1Lehrstuhl fur Allgemeine und Theor. Elektrotech., Erlangen-Nurnberg Univ.

IEEE Transactions on Neural Networks
|January 1, 1995
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

[Clinical characteristics and surgical effect observation of congenital aniridia combined with cataract].

[Zhonghua yan ke za zhi] Chinese journal of ophthalmology·2017
Same author

Risk factors for extra-pulmonary tuberculosis compared to pulmonary tuberculosis.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2009
Same author

A neural approach for control of nonlinear systems with feedback linearization.

IEEE transactions on neural networks·2008
Same author

Use of parenteral testosterone prior to hypospadias surgery.

Pediatric surgery international·2003
Same author

Nonlinear model-based predictive control of non-depolarizing muscle relaxants using neural networks.

Journal of clinical monitoring and computing·2003
Same author

Hepatic Schistosomiasis japonica in a patient with gallstones and bile duct stones--a case report.

The Kaohsiung journal of medical sciences·2001
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 paper introduces a generalized canonical representation for piecewise-linear (PWL) functions to mathematically support mapping networks. This novel approach enables the development of canonical PWL networks, offering new theoretical insights into neural network architectures.

Area of Science:

  • Mathematics
  • Computer Science
  • Artificial Intelligence

Background:

  • Piecewise-linear (PWL) approximation is crucial in mathematical and circuit simulation theories.
  • The canonical representation is a key concept within PWL representation theory.
  • Theoretical aspects of PWL representation in neural networks remain underexplored.

Purpose of the Study:

  • To modify and generalize the canonical representation theory for PWL functions.
  • To apply this modified theory as mathematical support for mapping networks.
  • To introduce a new class of networks: canonical PWL networks.

Main Methods:

  • Generalizing the canonical representation to a "higher-level" form.
  • Proving the availability of the generalized canonical representation within PWL functions.

Related Experiment Videos

  • Applying the modified theory to analyze multilayer perceptron-like (MLPL) networks.

    • Main Results:

    • A generalized canonical representation for PWL functions is established.
    • The canonical PWL feature of MLPL networks is investigated.
    • A new network implementation, the standard canonical PWL network, is proposed.
    • The family of canonical PWL networks is defined and shown to be practically meaningful.

    Conclusions:

    • The modified PWL representation theory provides a novel mathematical framework for mapping networks.
    • The introduction of canonical PWL networks offers a new conceptualization for neural network architectures.
    • This work bridges theoretical PWL representation with practical neural network design.