LoboVault Home
 

A Synthesis of Gradient and Hamiltonian Dynamics Applied to Learning in Neural Networks

LoboVault

Please use this identifier to cite or link to this item: http://hdl.handle.net/1928/91

A Synthesis of Gradient and Hamiltonian Dynamics Applied to Learning in Neural Networks

Show simple item record

dc.contributor.author Howse, J.W. en_US
dc.contributor.author Abdallah, C.T. en_US
dc.contributor.author Heileman, G.L. en_US
dc.date.accessioned 2006-03-10T07:23:56Z
dc.date.available 2006-03-10T07:23:56Z
dc.date.issued 1995-07-27T04:17:13Z
dc.identifier.uri http://hdl.handle.net/1928/91
dc.description Technical Report en_US
dc.description.abstract The 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.sponsorship This research was supported by a grant from Boeing Computer Services under Contract W-300445. en_US
dc.format.extent 526172 bytes
dc.format.extent 1888 bytes
dc.format.extent 36866 bytes
dc.format.mimetype application/pdf
dc.format.mimetype text/plain
dc.format.mimetype text/plain
dc.language.iso en_US en_US
dc.relation.ispartofseries EECE-TR-95-003 en_US
dc.subject Dynamical systems en_US
dc.subject System Identification en_US
dc.title A Synthesis of Gradient and Hamiltonian Dynamics Applied to Learning in Neural Networks en_US
dc.type Technical Report en_US


Files in this item

Files Size Format View
TR_EECE95_003.pdf 513.8Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

UNM Libraries

Search LoboVault


Advanced Search

Browse

My Account