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

A rapid supervised learning neural network for function interpolation and approximation.

¹Dept. of Comput. Sci. and Eng., Wright State Univ., Dayton, OH.

IEEE Transactions on Neural Networks

|January 1, 1996

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

Modifiable factors related to 7-year renal outcomes in subjects with type 2 diabetes and chronic kidney disease stage 3.

Journal of postgraduate medicine·2020

Same author

Re-focusing on Agnathia-Otocephaly complex.

Clinical oral investigations·2020

Same author

YAP/TAZ Regulate Elevation and Bone Formation of the Mouse Secondary Palate.

Journal of dental research·2020

Same author

First trimester placental vascular indices and volume by three-dimensional ultrasound in pre-gravid overweight women.

Placenta·2019

Same author

[Study on the mechanism of serotype conversion of historical isolates of <i>Shigella flexneri</i>].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2018

Same author

Axillary web syndrome following epidermal inclusion cyst: a case report and literature review.

Clinical and experimental dermatology·2018

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 novel neural network architecture and instant learning algorithm for efficient, one-shot training. It effectively handles data by approximating or interpolating, even with outliers, demonstrating promising experimental results.

Area of Science:

Artificial Intelligence
Machine Learning
Neural Networks

Background:

Iterative training algorithms are common in neural networks.
Handling noisy or outlier data can be challenging for standard algorithms.

Purpose of the Study:

To present a novel neural network architecture and an instant learning algorithm.
To enable rapid, one-shot training for single-hidden layer neural networks.
To develop methods for handling outlier data during training.

Main Methods:

A single-hidden layer neural network architecture is proposed.
An instant learning algorithm for rapid weight determination is introduced.
A robust weighted least squares method is presented for outlier elimination.

Related Experiment Videos

Main Results:

The proposed network requires a maximum of N-r-1 hidden nodes for N-pattern training sets.
The algorithm achieves "one-shot" off-line training, significantly faster than iterative methods.
The robust weighted least squares algorithm approximates data, effectively handling outliers.

Conclusions:

The novel architecture and instant learning algorithm offer efficient and rapid training.
The robust method successfully addresses outlier data, improving approximation accuracy.
Experimental results validate the effectiveness and advantages of the proposed approach.