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… (More)
DOI: 10.1109/IJCNN.1999.830755

Topics

6 Figures and Tables

Slides referencing similar topics