LoboVault Home

An application of gradient-like dynamics to neural networks


Please use this identifier to cite or link to this item: http://hdl.handle.net/1928/20392

An application of gradient-like dynamics to neural networks

Show simple item record

dc.contributor.author Abdallah, Chaouki T.
dc.contributor.author Howse, James W.
dc.contributor.author Heileman, Gregory L.
dc.date.accessioned 2012-04-16T22:25:49Z
dc.date.available 2012-04-16T22:25:49Z
dc.date.issued 1994-03-29
dc.identifier.citation Southcon/94. Conference Record: 92-96 en_US
dc.identifier.uri http://hdl.handle.net/1928/20392
dc.description Digital Object Identifier : 10.1109/SOUTHC.1994.498081 en_US
dc.description.abstract This paper reviews a formalism that enables the dynamics of a broad class of neural networks to be understood. This formalism is then applied to a specific network and the predicted and simulated behavior of the system are compared. The purpose of this work is to utilise a model of the dynamics that also describes the phase space behavior and structural stability of the system. This is achieved by writing the general equations of the neural network dynamics as a gradient-like system. In this paper it is demonstrated that a network with additive activation dynamics and Hebbian weight update dynamics can be expressed as a gradient-like system. An example of an S-layer network with feedback between adjacent layers is presented. It is shown that the process of weight learning is stable in this network when the learned weights are symmetric. Furthermore, the weight learning process is stable when the learned weights are asymmetric, provided that the activation is computed using only the symmetric part of the weights. en_US
dc.description.sponsorship IEEE en_US
dc.language.iso en_US en_US
dc.publisher IEEE en_US
dc.subject Application software en_US
dc.subject Computational modeling en_US
dc.subject Chaos en_US
dc.title An application of gradient-like dynamics to neural networks en_US
dc.type Article en_US

Files in this item

Files Size Format View
Abdallah Howse ... ics to neural networks.pdf 372.2Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

UNM Libraries

Search LoboVault


My Account