Ronald J. Williams  Home/Search
Context Related
| ph.tn.tudelft.nl/~di...nn_control.ps.gz neu.edu/pub/people...controlchap90.ps cwi.nl/~mbj/emergent...nn_control.ps.gz Cached: PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
PS.gz PS Image Update HelpFrom: ph.tn.tudelft.nl/~dick/ai/ (more) From: neu.edu/home/rjw/pubs (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Introduction The purpose of this chapter is to provide an introductory overview of some of the current research efforts directed toward adapting the weights in connectionist networks having feedback connections. While much of the recent emphasis in the field has been on multilayer networks having no such feedback connections, it is likely that the use of recurrently connected networks will be of particular importance for applications to the control of dynamical systems. Following the approach... (Update)
Similar documents based on text: More All
0.0: Analysis of Some Incremental Variants of Policy Iteration: .. - Williams, Baird, III (1993) (Correct)
0.0: Connectionist Learning for Control: An Overview - Barto (1989) (Correct)
0.0: A Mathematical Analysis Of Actor-Critic Architectures For.. - Williams (1990) (Correct)
BibTeX entry: (Update)
R. J. Williams, Adaptive State Representation and Estimation Using Recurrent Connectionist Networks, chapter 4, pages 97--114. MIT Press, Cambridge, MA, 1990. http://citeseer.ist.psu.edu/williams90adaptive.html More
@incollection{ williams90adaptive,
author = "Ronald J. Williams",
title = "Adaptive State Representation and Estimation Using Recurrent Connectionist Networks",
booktitle = "Neural networks for control",
publisher = "M.I.T. Press",
address = "Cambridge, Mass",
editor = "W. Thomas Miller and Richard S. Sutton and Paul J. Werbos",
pages = "97--114",
year = "1990",
url = "citeseer.ist.psu.edu/williams90adaptive.html" }
Citations (may not include all citations):644 Finding structure in time - Elman - 1988
412 Language identification in the limit (context) - Gold - 1967
373 Adaptive Signal Processing (context) - Widrow, Stearns - 1985
269 A learning algorithm for continually running fully recurrent.. - Williams, Zipser
268 Neurons with graded response have collective computational p.. (context) - Hopfield - 1984
253 Beyond regression: new tools for prediction and analysis in .. (context) - Werbos - 1974
190 Inductive inference: theory and methods (context) - Angluin, Smith - 1983
127 Attractor dynamics and parallelism in a connectionist sequen.. (context) - Jordan - 1986
123 Scene labeling by relaxation operations (context) - Rosenfeld, Hummel et al. - 1976
116 Finite-state automata and simple recurrent networks (context) - Cleeremans, Servan-Schreiber et al. - 1989
106 Connectionist models and their properties (context) - Feldman, Ballard - 1982
104 Learning state space trajectories in recurrent neural networ.. (context) - Pearlmutter - 1989
70 Experimental analysis of the real-time recurrent learning al.. (context) - Williams, Zipser
67 The utility driven dynamic error propagation network (context) - Robinson, Fallside - 1987
48 A learning rule for asynchronous perceptrons with feedback i.. (context) - Almeida - 1987
[Article contains additional citations not shown here]
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC