A stable second order method for training back propagation networksA simple method for improving the learning rate of the back-propagation algorithm is described. The basis of the method is that approximate second order corrections can be incorporated in the output units. The extended method leads to significant improvements in the convergence rate.
Document ID
19940034800
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Nachtsheim, Philip R. (NASA Ames Research Center Moffett Field, CA, United States)
Date Acquired
August 16, 2013
Publication Date
January 1, 1993
Publication Information
Publication: In: AIAA Computing in Aerospace Conference, 9th, San Diego, CA, Oct. 19-21, 1993, Technical Papers. Pt. 1 (A94-11401 01-62)
Publisher: American Institute of Aeronautics and Astronautics