Synthesis of feedforward networks in supremum error bound.

Synthesis of feedforward networks in supremum error bound. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Synthesis of feedforward networks in supremum error bound. Abstract Text:

K Ciesielski,J P Sacha,K J Cios,

The main result of this paper is a constructive proof of a formula for the upper bound of the approximation error in L/sub /spl infin// (supremum norm) of multidimensional functions by feedforward networks with one hidden layer of sigmoidal units and a linear output. This result is applied to formulate a new method of neural-network synthesis. The result can also be used to estimate complexity of the maximum-error network and/or to initialize that network's weights. An example of the network synthesis is given.

Synthesis of feedforward networks in supremum error bound. Publishing Authors By Initials

K Ciesielski,JP Sacha,KJ Cios,

For similar abstracts research abstracts see: abstracts research

PUBMED ID PMID:

MEDLINE DATE:

Synthesis of feedforward networks in supremum error bound. Journal Published:

PUBLICATION TYPE: Journal Article

Journal: IEEE transactions on neural networks / a publicati

VOLUME: 11

Page Numbers: 1213-27

Journal Abbreviation:

ISSN: 1045-9227

DAY: 5

MONTH: 02

YEAR: 2000

Synthesis of feedforward networks in supremum error bound. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 101211035

Synthesis of feedforward networks in supremum error bound. Keywords Mesh Terms:

KEYWORDS:

MESH TERMS:

Chemical & Substance for Abstract: Synthesis of feedforward networks in supremum error bound. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Synthesis of feedforward networks in supremum error bound.

AFFILIATION: Dept. of Math., West Virginia Univ., Morgantown, WV, USA.

Country: United States

AGENCY:

GRANT:

ACRONYM:

MEDLINETA: IEEE Trans Neural Netw

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Synthesis of feedforward networks in supremum error bound Related Publications

• A hidden Markov model for predicting protein interfaces.
• A very simple spiking neuron model that allows for modeling of large, complex systems.
• ClusFCM: AN ALGORITHM FOR PREDICTING PROTEIN FUNCTIONS USING HOMOLOGIES AND PROTEIN INTERACTIONS.
• Epileptic seizure detection.
• Proteomic data mining using predicted peptide chromatographic retention times.
• Solving graph algorithms with networks of spiking neurons.
• Synthesis of feedforward networks in supremum error bound.