Show simple item record

dc.contributor.authorLilai Yan
dc.contributor.authorC. James Li
dc.contributor.authorTung-Yung Huang
dc.date.accessioned2017-05-08T23:49:47Z
dc.date.available2017-05-08T23:49:47Z
dc.date.copyrightMarch, 1996
dc.date.issued1996
dc.identifier.issn0022-0434
dc.identifier.otherJDSMAA-26220#132_1.pdf
dc.identifier.urihttp://yetl.yabesh.ir/yetl/handle/yetl/116751
dc.description.abstractThis paper describes a new learning algorithm for time-varying recurrent neural networks whose weights are functions of time instead of scalars. First, an objective functional that is a function of the weight functions quantifying the discrepancies between the desired outputs and the network’s outputs is formulated. Then, dynamical optimization is used to derive the necessary conditions for the extreme of the functional. These necessary conditions result in a two-point boundary-value problem. This two-point boundary-value problem is subsequently solved by the Hilbert function space BFGS quasi-Newton algorithm, which is obtained by using the dyadic operator to extend the Euclidean space BFGS method into an infinite-dimensional, real Hilbert space. Finally, the ability of the network and the learning algorithm is demonstrated in the identification of three simulated nonlinear systems and a resistance spot welding process.
dc.publisherThe American Society of Mechanical Engineers (ASME)
dc.titleFunction Space BFGS Quasi-Newton Learning Algorithm for Time-Varying Recurrent Neural Networks
dc.typeJournal Paper
dc.journal.volume118
dc.journal.issue1
dc.journal.titleJournal of Dynamic Systems, Measurement, and Control
dc.identifier.doi10.1115/1.2801133
dc.journal.fristpage132
dc.journal.lastpage138
dc.identifier.eissn1528-9028
dc.keywordsArtificial neural networks
dc.keywordsAlgorithms
dc.keywordsBoundary-value problems
dc.keywordsFunctions
dc.keywordsNetworks
dc.keywordsScalars
dc.keywordsWeight (Mass)
dc.keywordsWelding
dc.keywordsElectrical resistance
dc.keywordsNonlinear systems AND Optimization
dc.treeJournal of Dynamic Systems, Measurement, and Control:;1996:;volume( 118 ):;issue: 001
dc.contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record