Utilising Local Model Neural Network Jacobian Information in Neurocontrol

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Carrelli, David John
dc.date.accessioned 2006-11-16T13:01:07Z
dc.date.available 2006-11-16T13:01:07Z
dc.date.issued 2006-11-16T13:01:07Z
dc.identifier.uri http://hdl.handle.net/10539/1815
dc.description Student Number : 8315331 - MSc dissertation - School of Electrical and Information Engineering - Faculty of Engineering and the Built Environment en
dc.description.abstract In this dissertation an efficient algorithm to calculate the differential of the network output with respect to its inputs is derived for axis orthogonal Local Model (LMN) and Radial Basis Function (RBF) Networks. A new recursive Singular Value Decomposition (SVD) adaptation algorithm, which attempts to circumvent many of the problems found in existing recursive adaptation algorithms, is also derived. Code listings and simulations are presented to demonstrate how the algorithms may be used in on-line adaptive neurocontrol systems. Specifically, the control techniques known as series inverse neural control and instantaneous linearization are highlighted. The presented material illustrates how the approach enhances the flexibility of LMN networks making them suitable for use in both direct and indirect adaptive control methods. By incorporating this ability into LMN networks an important characteristic of Multi Layer Perceptron (MLP) networks is obtained whilst retaining the desirable properties of the RBF and LMN approach. en
dc.format.extent 2432813 bytes
dc.format.mimetype application/pdf
dc.language.iso en en
dc.subject neural networks en
dc.subject neurocontrol en
dc.subject neuro control en
dc.subject Jacobian en
dc.subject local model network en
dc.subject radial basis function network en
dc.subject multilayer perceptron en
dc.subject adaptive control en
dc.subject on-line en
dc.subject recursive adaption en
dc.subject series inverse control en
dc.subject instantaneous linearization en
dc.subject singular value decomposition en
dc.subject SVD en
dc.title Utilising Local Model Neural Network Jacobian Information in Neurocontrol en
dc.type Thesis en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search WIReDSpace


Advanced Search

Browse

My Account

Statistics