Martin Riedmiller  Home/Search
Context Related
| amy.informatik.uos...rprop.details.ps.Z Cached: PS.gz PS 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.
Image Update HelpPS.gz PS PDF From: amy.informatik.uos.de/riedmill... (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: a change in sign, there should be no adaptation in the succeeding learning step. In practice, this can be achieved by setting := 0 in the above adaptation rule (see also the description of the algorithm in the following section). In order to reduce the number of freely adjustable parameters, often leading to a tedious search in parameter space, the increase and decrease factor are set to fixed values. The choice of the decrease factor j was lead by the following considerations. If a jump... (Update)
Similar documents based on text: More All
0.9: Rprop - Description and Implementation Details - Riedmiller (1994) (Correct)
0.6: A Direct Adaptive Method for Faster Backpropagation.. - Riedmiller, Braun (1993) (Correct)
0.5: Controlling an Inverted Pendulum by Neural Plant Identification - Martin Riedmiller (1993) (Correct)
Related documents from co-citation: More All
3: A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorith.. - Riedmiller, Braun - 1993
2: The CascadeCorrelation Learning: A Projection Pursuit Learning Perspective (context) - Hwang, You et al. - 1996
2: An empirical study of learning speeds in backpropagation networks - Fahlman - 1988
BibTeX entry: (Update)
M. Riedmiller and H. Braun. RPROP -- Description and Implementation Details. Technical Report. Universitat Karlsruhe, 1994. http://citeseer.ist.psu.edu/riedmiller94rprop.html More
@misc{ riedmiller94rprop,
author = "M. Riedmiller and H. Braun",
title = "RPROP -- Description and Implementation Details",
text = "M. Riedmiller and H. Braun. RPROP -- Description and Implementation Details.
Technical Report. Universitat Karlsruhe, 1994.",
year = "1994",
url = "citeseer.ist.psu.edu/riedmiller94rprop.html" }
Citations (may not include all citations):237 A direct adaptive method for faster backpropagation learning.. - Riedmiller, Braun - 1993
162 Increased rates of convergence through learning rate adaptat.. (context) - Jacobs - 1988
30 Supersab: Fast adaptive backpropagation with good scaling pr.. (context) - Tollenaere - 1990
27 Advanced supervised learning in multilayer perceptrons - fro.. - Riedmiller - 1994
3 Untersuchungen zu Konvergenz und Generalisierungsverhalten u.. (context) - Riedmiller - 1993
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://amy.informatik.uos.de/riedmiller/publications/): More
Reinforcement Learning for Stochastic Cooperative.. - Lauer, Riedmiller (Correct)
Learning to Control at Multiple Time Scales - Schoknecht, Riedmiller (2003) (Correct)
A Neural Reinforcement Learning Approach to Learn Local.. - Riedmiller, Riedmiller (1999) (Correct)
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