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

Circular backpropagation networks for classification.

S Ridella¹, S Rovetta, R Zunino

¹Dept. of Biophys. and Electron. Eng., Genoa Univ.

IEEE Transactions on Neural Networks

|January 1, 1997

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

Imaging artifacts in MRI simulators.

The neuroradiology journal·2013

Same author

Study of bound water of poly-adenine using high frequency dielectric measurements.

Biophysical journal·2009

Same author

Representation and generalization properties of class-entropy networks.

IEEE transactions on neural networks·2008

Same author

Worst case analysis of weight inaccuracy effects in multilayer perceptrons.

IEEE transactions on neural networks·2008

Same author

Circular backpropagation networks embed vector quantization.

IEEE transactions on neural networks·2008

Same author

Empirical measure of multiclass generalization performance: the K-winner machine case.

IEEE transactions on neural networks·2008

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 mapping network model that unifies surface-based and prototype-based classification schemes. This enhanced multilayer perceptron offers improved generalization and performance for pattern classification tasks.

Area of Science:

Machine Learning
Artificial Intelligence
Pattern Recognition

Background:

Mapping networks are versatile tools for diverse tasks.
Existing classification models have limitations in representation paradigms.
Multilayer perceptrons (MLPs) are widely used but can be improved.

Purpose of the Study:

To present a standardized representation for mapping networks.
To introduce a modified multilayer perceptron for enhanced pattern classification.
To unify surface-based and prototype-based classification schemes within a single model.

Main Methods:

Developed a modified multilayer perceptron architecture.
Unified surface-based and prototype-based representation paradigms.

Related Experiment Videos

Utilized backpropagation for training the proposed network.

Assessed generalization performance using Vapnik-Chervonenkis dimension and cover capacity.

Main Results:

The proposed model unifies key classification paradigms while remaining backpropagation-trainable.
Theoretical analysis suggests optimal properties for the modified MLP.
Experimental results demonstrate superior performance compared to standard MLPs and Gaussian radial basis functions networks.
The model shows improved representation properties and generalization capabilities.

Conclusions:

The modified multilayer perceptron offers significant advantages for pattern classification.
This unified approach enhances network representation and generalization performance.
The proposed model represents a theoretically optimal and practically effective advancement in mapping networks.