dc.creator | Parlos, Alexander G. | |
dc.creator | Atiya, Amir F. | |
dc.date.accessioned | 2019-06-17T16:59:47Z | |
dc.date.available | 2019-06-17T16:59:47Z | |
dc.date.issued | 2005-11-08 | |
dc.identifier.uri | https://hdl.handle.net/1969.1/176799 | |
dc.description.abstract | A method for training a recurrent network represented by x(k+1)=f(W x(k)), where W is a weight matrix, x is the output of the network, and K is a time index includes (a) determining the weight matrix at a first time increment, (b) incrementing the time increment associated with a received data point, and (c) determining a change in the weight matrix at the incremented time interval according to the formula: Δ W(K)=Δ W(K-1)+η γ(K)xT(K-1) V-1(K-1)-B(K-1) V-1(K-1) x (K-1)[V-1(K-1) x (K-1)]T1+xT(K-1) V-1(K-1) x (K-1) | en |
dc.language | eng | |
dc.publisher | United States. Patent and Trademark Office | |
dc.rights | Public Domain (No copyright - United States) | en |
dc.rights.uri | http://rightsstatements.org/vocab/NoC-US/1.0/ | |
dc.title | Method and system for training a recurrent network | en |
dc.type | Utility patent | en |
dc.format.digitalOrigin | reformatted digital | en |
dc.description.country | US | |
dc.contributor.assignee | The Texas A&M University System | |
dc.identifier.patentapplicationnumber | 09/823599 | |
dc.subject.uspcprimary | 706/30 | |
dc.subject.uspcother | 706/15 | |
dc.subject.uspcother | 706/26 | |
dc.date.filed | 2001-03-30 | |
dc.publisher.digital | Texas A&M University. Libraries | |
dc.subject.cpcprimary | G06N 3/08 | |