smagt@fwi.uva.nl (Patrick van der Smagt) (08/31/90)
I am looking for THE reference (if existing) on conjugate
gradient training of feed-forward networks. Is the first
implementer
%A E. Barnard
%A R. Cole
%T A neural-net training program based on
conjugate-gradient optimization
%I Oregon Graduate Center
%R CSE 89--014
%D 1898
?
Patrick van der Smagt /\/\
\ /
Organization: Faculty of Mathematics & Computer Science / \
University of Amsterdam, Kruislaan 409, _ \/\/ _
NL-1098 SJ Amsterdam, The Netherlands | | | |
Phone: +31 20 525 7466 | | /\/\ | |
Telex: 10262 hef nl | | \ / | |
Fax: +31 20 592 5155 | | / \ | |
email: smagt@fwi.uva.nl | | \/\/ | |
| \______/ |
\________/
/\/\
\ /
/ \
\/\/
``The opinions expressed herein are the author's only and do
not necessarily reflect those of the University of Amsterdam.''
ins_atge@jhunix.HCF.JHU.EDU (Thomas G Edwards) (09/01/90)
In article <1217@carol.fwi.uva.nl> smagt@fwi.uva.nl (Patrick van der Smagt) writes: >I am looking for THE reference (if existing) on conjugate >gradient training of feed-forward networks. Is the first >implementer Good question. There is also A.H. Kramer and A. Sangiovanni-Vincentelli, "Efficient Parallel Learning Algorithms for Neural Networks." In _Advances_in_Neural_Information_ Processing_Systems_1 (D.S. Touretzky, editor), pages 40-48. Morgan Kaufmann, San Mateo, CA, 1989. Compares fixed step size gradient descent with steepest-descent and conjugate-gradient. -Thomas Edwards