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

Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification.

D F Specht1

  • 1Lockheed Missiles and Space Co. Inc., Palo Alto, CA.

IEEE Transactions on Neural Networks
|January 1, 1990
PubMed
Summary

Two classification methods, probabilistic neural networks (PNN) and polynomial Adaline, offer fast, one-pass learning for neural networks. They provide complementary advantages for various database sizes and application needs.

Related Concept Videos

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Classification of Systems-I01:26

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A general regression neural network.

IEEE transactions on neural networks·1991
Same author

Multi-frame hardcopy output device for an ultrasonic sector scanner.

Biomedical sciences instrumentation·1980
Same author

Clinical evaluation of a new computerized arrhythmia monitoring system.

Heart & lung : the journal of critical care·1975
Same author

Classification of electrocardiograms using the Polynomial Discriminant Method of pattern classification.

Biomedical sciences instrumentation·1968
Same author

Vectorcardiographic diagnosis using the polynomial discriminant method of pattern recognition.

IEEE transactions on bio-medical engineering·1967

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Pattern Recognition

Background:

  • Classification tasks are fundamental in machine learning and data analysis.
  • Traditional methods often require multiple passes through data, increasing computational cost.
  • Efficient algorithms are needed for handling large datasets and real-time applications.

Purpose of the Study:

  • To review and compare two one-pass learning classification methods: probabilistic neural networks (PNN) and polynomial Adaline.
  • To analyze their performance against multipass backpropagation networks.
  • To discuss the complementary advantages and disadvantages of PNN and polynomial Adaline for different applications.

Main Methods:

  • Probabilistic Neural Network (PNN): A Bayes strategy-based classifier utilizing nonparametric probability density function estimators.

Related Experiment Videos

  • Polynomial Adaline: Another classification method employing nonparametric estimators and one-pass learning.
  • Performance comparison using multipass backpropagation networks as a benchmark.

    • Main Results:

    • Both PNN and polynomial Adaline implement identical decision boundaries.
    • PNN excels in ease of use and speed for moderate-sized databases.
    • Polynomial Adaline offers advantages for very large databases and applications prioritizing classification speed over training speed.

    Conclusions:

    • PNN and polynomial Adaline are complementary techniques in neural network classification.
    • The choice between PNN and polynomial Adaline depends on database size and specific application requirements (training vs. classification speed).
    • These one-pass learning methods offer efficient alternatives to multipass algorithms.