Improving the Rprop Learning Algorithm

Improving the Rprop Learning Algorithm (2000)

Cached

Download Links

by Christian Igel , Michael Hüsken

Venue:	PROCEEDINGS OF THE SECOND INTERNATIONAL SYMPOSIUM ON NEURAL COMPUTATION (NC 2000)
Citations:	35 - 7 self

BibTeX

@MISC{Igel00improvingthe,
    author = {Christian Igel and Michael Hüsken},
    title = {Improving the Rprop Learning Algorithm},
    year = {2000}
}

Bookmark

OpenURL

Abstract

The Rprop algorithm proposed by Riedmiller and Braun is one of the best performing first-order learning methods for neural networks. We introduce modifications of the algorithm that improve its learning speed. The resulting speedup is experimentally shown for a set of neural network learning tasks as well as for artificial error surfaces.

Citations

505	A direct adaptive method for faster back-propagation learning: the RPROP algorithm - Riedmiller, Braun - 1993
283	Increased rates of convergence through learning rate adaptation - Jacobs
156	A Set of Neural Network Benchmark Problems and Benchmarking Rules - Prechelt - 1994
118	Adapting arbitrary normal mutation distributions in evolution strategies: the covariance matrix adaptation - Hansen, Ostermeier - 1996
98	Convergence of the Back-Propagation Method - Vogl, Mangis, et al. - 1988
93	Efficient BackProp - LeCun, Bottou, et al. - 1998
85	PROBEN1 — A set of benchmarks and benchmarking rules for neural network training algorithms,” Fakultät für Informatik, Universität - Prechelt - 1994
74	Advanced supervised learning in multi-layer perceptrons – From backpropagation to adaptive learning algorithms - Riedmiller - 1994
50	Convergence properties of evolution strategies with the derandomized covariance matrix adaptation: The (μ/μi,λ)-CMA-ES. In 5th European congress on intelligent techniques and soft computing (pp. 650–654). Neuroinform (2012) 10:199–218 - Hansen, Ostermeier - 1997
49	Supersab: fast adaptive backpropagation with good scaling properties - tollenaere - 1990
40	Learning internal representations by error backpropagation - Rumelhart, Hinton, et al. - 1986
39	Speeding up backpropagation - Silva, Almeida - 1990
36	Comparison of optimized backpropagation algorithms - Schiffman, Joost, et al. - 1993
34	Acceleration techniques for the backpropagation algorithm - Silva, Almeida - 1990
17	Speeding up backpropagation algorithm by using cross-entropy combined with pattern normalization - Schiffmann, Joost
16	Neural Smithing - Reed, Marks - 1999
11	Artificial neural networks for solving ordinary and partial differential equations - Lagaris, Likas, et al. - 1998
8	Neural network structure design by evolutionary programming - McDonnell, Waagen - 1993
6	Neural network methods for boundary value problems defined in arbitrarily shaped domains - Lagaris, Likas, et al. - 1998
4	Fast adaptation of the solution of differential equations to changing constraints - Hsken, Goerick, et al. - 2000
1	Neuronale Nctzc: Optimicrung dutch Lemon und Evolution - Braun - 1997