Share Email Print
cover

Proceedings Paper

Transform neural network for Fourier detection task
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Complex-valued weights are used in the first layer of a feed forward neural network to produce a `transform' neural network. This network was applied to a phase-uncertain sine wave detection task against a Gaussian white noise background. When compared with results of a human observer study on this task by Burgess et al., performance of the transform network was found to be nearly equal to that of an ideal observer and far superior to that of the human observers. Performance was found to be dramatically affected by initial values of the weights, which is explained in terms of concepts from statistical decision theory.

Paper Details

Date Published: 21 May 1999
PDF: 6 pages
Proc. SPIE 3661, Medical Imaging 1999: Image Processing, (21 May 1999); doi: 10.1117/12.348623
Show Author Affiliations
David G. Brown, Ctr. for Devices and Radiological Health/FDA (United States)
Mary S. Pastel, Ctr. for Devices and Radiological Health/FDA (United States)
Kyle J. Myers, Ctr. for Devices and Radiological Health/FDA (United States)


Published in SPIE Proceedings Vol. 3661:
Medical Imaging 1999: Image Processing
Kenneth M. Hanson, Editor(s)

© SPIE. Terms of Use
Back to Top