DeepNet: An ultrafast neural learning code for seismic imaging

J. Barhen; David Reister; V. Protopopescu

DeepNet: An ultrafast neural learning code for seismic imaging

J. Barhen, David Reister, V. Protopopescu

Computational Sciences & Engineering Div

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

A feed-forward multilayer neural net is trained to learn the correspondence between seismic data and well logs. The introduction of a virtual input layer, connected to the nominal input layer through a special nonlinear transfer function, enables ultrafast (single iteration), near-optimal training of the net using numerical algebraic techniques. A unique computer code, named DeepNet, has been developed, that has achieved, in actual field demonstrations, results unattainable to date with industry standard tools.

Original language	English
Pages	3779-3784
Number of pages	6
State	Published - 1999
Event	International Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA Duration: Jul 10 1999 → Jul 16 1999

Conference

Conference	International Joint Conference on Neural Networks (IJCNN'99)
City	Washington, DC, USA
Period	07/10/99 → 07/16/99

Cite this

@conference{023b96f8c05a421088ff66bca8f587a8,

title = "DeepNet: An ultrafast neural learning code for seismic imaging",

abstract = "A feed-forward multilayer neural net is trained to learn the correspondence between seismic data and well logs. The introduction of a virtual input layer, connected to the nominal input layer through a special nonlinear transfer function, enables ultrafast (single iteration), near-optimal training of the net using numerical algebraic techniques. A unique computer code, named DeepNet, has been developed, that has achieved, in actual field demonstrations, results unattainable to date with industry standard tools.",

author = "J. Barhen and David Reister and V. Protopopescu",

year = "1999",

language = "English",

pages = "3779--3784",

note = "International Joint Conference on Neural Networks (IJCNN'99) ; Conference date: 10-07-1999 Through 16-07-1999",

}

TY - CONF

T1 - DeepNet

T2 - International Joint Conference on Neural Networks (IJCNN'99)

AU - Barhen, J.

AU - Reister, David

AU - Protopopescu, V.

PY - 1999

Y1 - 1999

N2 - A feed-forward multilayer neural net is trained to learn the correspondence between seismic data and well logs. The introduction of a virtual input layer, connected to the nominal input layer through a special nonlinear transfer function, enables ultrafast (single iteration), near-optimal training of the net using numerical algebraic techniques. A unique computer code, named DeepNet, has been developed, that has achieved, in actual field demonstrations, results unattainable to date with industry standard tools.

AB - A feed-forward multilayer neural net is trained to learn the correspondence between seismic data and well logs. The introduction of a virtual input layer, connected to the nominal input layer through a special nonlinear transfer function, enables ultrafast (single iteration), near-optimal training of the net using numerical algebraic techniques. A unique computer code, named DeepNet, has been developed, that has achieved, in actual field demonstrations, results unattainable to date with industry standard tools.

UR - http://www.scopus.com/inward/record.url?scp=0033311609&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0033311609

SP - 3779

EP - 3784

Y2 - 10 July 1999 through 16 July 1999

ER -

DeepNet: An ultrafast neural learning code for seismic imaging

Abstract

Conference

Other files and links

Fingerprint

Cite this