Show simple item record

dc.contributor.authorHowse, J.W.en_US
dc.contributor.authorAbdallah, C.T.en_US
dc.contributor.authorHeileman, G.L.en_US
dc.date.accessioned2006-03-10T07:23:56Z
dc.date.available2006-03-10T07:23:56Z
dc.date.issued1995-07-27T04:17:13Z
dc.identifier.urihttp://hdl.handle.net/1928/91
dc.descriptionTechnical Reporten_US
dc.description.abstractThe process of model learning can be considered in two stages: model selection and parameter estimation. In this paper a technique is presented for constructing dynamical systems with desired qualitative properties. The approach is based on the fact that an n-dimensional nonlinear dynamical system can be decomposed into one gradient and (n - 1) Hamiltonian systems. Thus, the model selection stage consists of choosing the gradient and Hamiltonian portions appropriately so that a certain behavior is obtainable. To estimate the parameters, a stably convergent learning rule is presented. This algorithm is proven to converge to the desired system trajectory for all initial conditions and system inputs. This technique can be used to design neural network models which are guaranteed to solve certain classes of nonlinear identification problems.en_US
dc.description.sponsorshipThis research was supported by a grant from Boeing Computer Services under Contract W-300445.en_US
dc.format.extent526172 bytes
dc.format.extent1888 bytes
dc.format.extent36866 bytes
dc.format.mimetypeapplication/pdf
dc.format.mimetypetext/plain
dc.format.mimetypetext/plain
dc.language.isoen_USen_US
dc.relation.ispartofseriesEECE-TR-95-003en_US
dc.subjectDynamical systemsen_US
dc.subjectSystem Identificationen_US
dc.titleA Synthesis of Gradient and Hamiltonian Dynamics Applied to Learning in Neural Networksen_US
dc.typeTechnical Reporten_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record