Publication: Backwards Differentiation in AD and Neural Nets: Past Links and New Opportunities
Introduction
Applications
Tools
Research Groups
Workshops
Publications
   List Publications
   Advanced Search
   Info
   Add Publications
My Account
About

Backwards Differentiation in AD and Neural Nets: Past Links and New Opportunities

- incollection -
 

Author(s)
Paul J. Werbos

Published in
Automatic Differentiation: Applications, Theory, and Implementations

Editor(s)
H. M. Bücker, G. Corliss, P. Hovland, U. Naumann, B. Norris

Year
2005

Publisher
Springer

Abstract
Backwards calculation of derivatives -- sometimes called the reverse mode, the full adjoint method, or backpropagation -- has been developed and applied in many fields. This paper reviews several strands of history, advanced capabilities and types of application -- particularly those which are crucial to the development of brain-like capabilities in intelligent control and artificial intelligence.

Cross-References
Bucker2005ADA

AD Theory and Techniques
History, Neural Networks

BibTeX
@INCOLLECTION{
         Werbos2005BDi,
       author = "Paul J. Werbos",
       title = "Backwards Differentiation in {AD} and Neural Nets: {P}ast Links and New
         Opportunities",
       editor = "H. M. B{\"u}cker and G. Corliss and P. Hovland and U. Naumann and B.
         Norris",
       booktitle = "Automatic Differentiation: {A}pplications, Theory, and Implementations",
       series = "Lecture Notes in Computational Science and Engineering",
       publisher = "Springer",
       year = "2005",
       abstract = "Backwards calculation of derivatives -- sometimes called the reverse mode, the full
         adjoint method, or backpropagation -- has been developed and applied in many fields. This paper
         reviews several strands of history, advanced capabilities and types of application -- particularly
         those which are crucial to the development of brain-like capabilities in intelligent control and
         artificial intelligence.",
       crossref = "Bucker2005ADA",
       ad_theotech = "History, Neural Networks",
       pages = "15--34",
       doi = "10.1007/3-540-28438-9_2"
}


back
  

Contact:
autodiff.org
Username:
Password:
(lost password)