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

Fault-tolerant training for optimal interpolative nets.

D Simon¹, H El-Sherief

¹TRW Syst. Integration Group, San Bernardino, CA.

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

Neutrophil apoptosis mediated by nicotinic acid receptors (GPR109A).

Cell death and differentiation·2007

Same author

Pharmacological inhibition of GSK-3 is not strictly correlated with a decrease in tyrosine phosphorylation of residues 216/279.

Journal of neuroscience research·2007

Same author

Type 2 diabetes mellitus: epidemiology, pathophysiology, unmet needs and therapeutical perspectives.

Diabetes & metabolism·2007

Same author

Density functional study of structural and electronic properties of small bimetallic silver-nickel clusters.

The journal of physical chemistry. A·2007

Same author

Increased lipopolysaccharide-induced tumour necrosis factor-alpha, interferon-gamma and interleukin-10 production in atopic dermatitis.

The British journal of dermatology·2007

Same author

Anaplasma phagocytophilum in dogs in Germany.

Zoonoses and public health·2007

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 fault-tolerant optimal interpolative (OI) classification network, enhancing robustness to neuron loss. This fault tolerance reduces neuron usage while preserving network generalization capabilities.

Area of Science:

Machine Learning
Artificial Intelligence
Neural Networks

Background:

The optimal interpolative (OI) classification network efficiently fits training data using minimal neurons.
Existing OI networks may lack robustness against neuron failure, potentially impacting performance.

Purpose of the Study:

To extend the optimal interpolative (OI) classification network with fault tolerance.
To enhance the network's robustness against the loss of individual neurons.
To maintain or improve generalization capabilities in the presence of faults.

Main Methods:

The optimal interpolative (OI) classification network was modified to incorporate fault tolerance mechanisms.
A recursive learning algorithm was developed for the fault-tolerant OI network.

Related Experiment Videos

Simulations were conducted to evaluate the performance of the fault-tolerant OI network.

Main Results:

Fault tolerance reduced the number of neurons generated during the learning process.
The fault-tolerant OI network maintained its generalization capabilities.
The recursive learning algorithm enabled relatively short training times.

Conclusions:

The fault-tolerant OI network offers improved robustness and efficiency.
This fault-tolerant approach is suitable for practical applications, as demonstrated by its successful testing on a navigation satellite selection problem.