Back to Results
First PageMeta Content
Dimensional analysis / Measurement


Stagewise Newton, differential dynamic programming, and neighboring optimum control for neural-network learning Eiji Mizutani and Stuart E. Dreyfus Abstract— The theory of optimal control is applied to multistage (i.e.
Add to Reading List

Document Date: 2008-07-16 21:59:51

Open Document

File Size: 143,59 KB

Share Result on Facebook

City

Washington / D.C. / Montreal Quebec / New York / Waltham / /

Company

Princeton University Press / John Wiley & Sons Inc. / Non-Linear Discrete Time Systems / Eq / Neural Information Processing Systems / BP / Neural Networks / MIT Press / /

Country

Canada / /

Currency

pence / /

/

Event

Force Majeure / /

Facility

Imperial College of Science / University of London / University of California / Tsing Hua University / /

IndustryTerm

nominal solution / gradient algorithms / aforementioned optimal-control algorithms / on-line learning / computing / backpropagation algorithms / on-line secondorder learning / triangular systems / nonlinear least squares algorithms / /

Organization

Connectionist Models Summer School / MIT / Faculty of Industrial Engineering and Operations Research / Princeton University / University of California / Berkeley / Imperial College of Science and Technology / U.S. Securities and Exchange Commission / Tsing Hua University / University of London / /

Person

Jarrell R. Elliott / James W. Demmel / Andrew G. Barto / David Mayne / D. Greenspan / Arthur E. Bryson / Jr. / Henry J. Kelley / Richard S. Sutton / Stuart E. Dreyfus / David H. Jacobson / Eiji Mizutani / Stephen R. McReynolds / Peter Dyer / /

ProgrammingLanguage

MATLAB / J / /

ProvinceOrState

New York / Massachusetts / /

Technology

infeasible DP algorithm / second-order algorithms / elaborate NN-learning algorithms / gradient algorithms / Newton algorithms / Second-order backpropagation algorithms / nonlinear least squares algorithms / machine learning / DP algorithm / /

SocialTag