Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Classification of linearly nonseparable patterns by linear threshold elements.

V P Roychowdhury¹, K Y Siu, T Kailath

¹Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN.

IEEE Transactions on Neural Networks

|January 1, 1995

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

Nurse-led sexual rehabilitation to rebuild sexuality and intimacy after treatment for gynaecological cancer: a randomised controlled trial (abridged secondary publication).

Hong Kong medical journal = Xianggang yi xue za zhi·2023

Same author

Chess players' fame versus their merit.

Applied economics letters·2015

Same author

A feasibility study of a psychoeducational intervention program for gynecological cancer patients.

European journal of oncology nursing : the official journal of European Oncology Nursing Society·2014

Same author

Stochastic modeling of a serial killer.

Journal of theoretical biology·2014

Same author

Eigenstructure approach to directions-of-arrival estimation in IR detector arrays.

Applied optics·2010

Same author

Climate change and the integrity of science.

Science (New York, N.Y.)·2010

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 explores perceptron learning for non-linearly separable data, revealing how linear threshold elements learn optimally even with errors. It identifies learnable subsets within complex datasets.

Area of Science:

Machine Learning
Computational Neuroscience
Pattern Recognition

Background:

Perceptron learning is well-understood for linearly separable data.
Limited knowledge exists on perceptron behavior with linearly nonseparable training sets.

Purpose of the Study:

To present novel results on the structure of linearly nonseparable training sets.
To analyze the behavior of perceptrons with linearly nonseparable input vectors.
To characterize what a perceptron can learn from nonseparable data.

Main Methods:

Formal characterization of linearly nonseparable training sets.
Definition of learnable structures for nonseparable patterns.
Computational complexity analysis of related learning problems.

Related Experiment Videos

Main Results:

Identified learnable input vectors and those causing errors for perceptrons.
Demonstrated that perceptrons learn the maximum possible from nonseparable sets.
Showed how to use linear threshold elements to learn large separable subsets.

Conclusions:

Perceptron learning algorithm performs optimally for nonseparable data.
Formal characterizations enable understanding of learnability limits.
This work advances the theory of perceptron learning beyond separable cases.