Search research articles

Search research articles

Related Experiment Videos

Multilayer neural networks and function reconstruction by using a priori knowledge.

L C Pedroza¹, C E Pedreira

¹Federal Center of Technology of Rio de Janeiro and Catholic University of Rio de Janeiro, Brazil. pedroza@cefet-rj.br

International Journal of Neural Systems

|November 24, 1999

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

Comparison between five pattern-based approaches for automated diagnostic classification of mature/peripheral B-cell neoplasms based on standardized EuroFlow flow cytometry immunophenotypic data.

Computers in biology and medicine·2025

Same author

A decision-tree approach for the differential diagnosis of chronic lymphoid leukemias and peripheral B-cell lymphomas.

Computer methods and programs in biomedicine·2019

Same author

From big flow cytometry datasets to smart diagnostic strategies: The EuroFlow approach.

Journal of immunological methods·2019

Same author

Automated database-guided expert-supervised orientation for immunophenotypic diagnosis and classification of acute leukemia.

Leukemia·2017

Same author

Impact of maternal education level on risk of low Apgar score.

Public health·2016

Same author

CLL-like B-lymphocytes are systematically present at very low numbers in peripheral blood of healthy adults.

Leukemia·2011

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

This study introduces a novel function approximation method using prior information, outperforming the Back-Propagation Algorithm with fewer parameters for better generalization. It

Area of Science:

Computational mathematics
Machine learning theory

Background:

Function approximation is crucial in various scientific domains.
Existing methods like the Back-Propagation Algorithm have limitations in parameter efficiency and generalization.

Purpose of the Study:

To propose a new methodology for function approximation.
To incorporate a priori information into the approximation process.
To analyze the proposed scheme's relationship with multilayer neural networks.

Main Methods:

Development of a novel function approximation scheme.
Theoretical analysis of the scheme's connection to multilayer neural networks.
Numerical validation of the proposed method.

Main Results:

Related Experiment Videos

The proposed method effectively approximates functions, especially limited spectrum functions.
Demonstrated a smaller number of free parameters compared to the Back-Propagation Algorithm.
Achieved improved generalization capabilities.

Conclusions:

The new methodology offers a more efficient alternative for function approximation.
The approach shows promise for applications requiring high generalization performance.
Further exploration of its theoretical and numerical properties is warranted.