Linked Life Data

19796915

Source:http://linkedlifedata.com/resource/pubmed/id/19796915

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
4
pubmed:dateCreated
2010-3-29
pubmed:abstractText
Neural networks applied in control loops and safety-critical domains have to meet more requirements than just the overall best function approximation. On the one hand, a small approximation error is required; on the other hand, the smoothness and the monotonicity of selected input-output relations have to be guaranteed. Otherwise, the stability of most of the control laws is lost. In this article we compare two neural network-based approaches incorporating partial monotonicity by structure, namely the Monotonic Multi-Layer Perceptron (MONMLP) network and the Monotonic MIN-MAX (MONMM) network. We show the universal approximation capabilities of both types of network for partially monotone functions. On a number of datasets, we investigate the advantages and disadvantages of these approaches related to approximation performance, training of the model and convergence.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:status
MEDLINE
pubmed:month
May
pubmed:issn
1879-2782
pubmed:author
pubmed:copyrightInfo
2009 Elsevier Ltd. All rights reserved.
pubmed:issnType
Electronic
pubmed:volume
23
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
471-5
pubmed:meshHeading
pubmed:year
2010
pubmed:articleTitle
Comparison of universal approximators incorporating partial monotonicity by structure.
pubmed:affiliation
OOO Siemens, Monitoring and Preventive Control group, 191186 Saint-Petersburg, Volynskiy Per. Dom 3A liter A, Russia. alexey.minin@siemens.com
pubmed:publicationType
Journal Article