Show simple item record

dc.contributor.authorC. James Li
dc.contributor.authorTaehee Kim
dc.date.accessioned2017-05-08T23:46:46Z
dc.date.available2017-05-08T23:46:46Z
dc.date.copyrightSeptember, 1995
dc.date.issued1995
dc.identifier.issn0022-0434
dc.identifier.otherJDSMAA-26216#411_1.pdf
dc.identifier.urihttp://yetl.yabesh.ir/yetl/handle/yetl/115059
dc.description.abstractA fully automatic feedforward neural network structural and weight learning algorithm is described. The Augmentation by Training with Residuals, ATR, requires neither guess of initial weight values nor the number of neurons in the hidden layer from users. The algorithm takes an incremental approach in which a hidden neuron is trained to model the mapping between the input and output of current exemplars, and is augmented to the existing network. The exemplars are then made orthogonal to the newly identified hidden neuron and used for the training of next hidden neuron. The improvement continues until a desired accuracy is reached. This new structural and weight learning algorithm is applied to the identification of a two-degree-of-freedom planar robot, a Van der Pol oscillator and a Mackay-Glass equation. The algorithm is shown to be effective in modeling all three systems and is far superior to a linear modeling scheme in the case of the robot.
dc.publisherThe American Society of Mechanical Engineers (ASME)
dc.titleA New Feedforward Neural Network Structural Learning Algorithm—Augmentation by Training With Residuals
dc.typeJournal Paper
dc.journal.volume117
dc.journal.issue3
dc.journal.titleJournal of Dynamic Systems, Measurement, and Control
dc.identifier.doi10.1115/1.2799132
dc.journal.fristpage411
dc.journal.lastpage415
dc.identifier.eissn1528-9028
dc.keywordsAlgorithms
dc.keywordsArtificial neural networks
dc.keywordsFeedforward control
dc.keywordsWeight (Mass)
dc.keywordsModeling
dc.keywordsRobots
dc.keywordsGlass
dc.keywordsNetworks AND Equations
dc.treeJournal of Dynamic Systems, Measurement, and Control:;1995:;volume( 117 ):;issue: 003
dc.contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record