Abstract
A learning algorithm for multilayer feedforward networks, RPROP (resilient propagation), is proposed. To overcome the inherent disadvantages of pure gradient-descent, RPROP performs a local adaptation of the weight-updates according to the behavior of the error function. Contrary to other adaptive techniques, the effect of the RPROP adaptation process is not blurred by the unforeseeable influence of the size of the derivative, but only dependent on the temporal behavior of its sign. This leads to an efficient and transparent adaptation process. The capabilities of RPROP are shown in comparison to other adaptive techniques.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Keywords
RpropBackpropagationComputer scienceAdaptation (eye)Feed forwardArtificial intelligenceProcess (computing)AlgorithmFunction (biology)Artificial neural networkRecurrent neural networkEngineeringTypes of artificial neural networksControl engineering
Affiliated Institutions
Related Publications
Generalization of Back propagation to Recurrent and Higher Order Neural Networks
A general method for deriving backpropagation algorithms for networks with recurrent and higher order networks is introduced. The propagation of activation in these networks is ...
Performance of CDMA mobile communication systems using antenna arrays
The use antenna arrays in cellular code division multiple access mobile communications is studied. Techniques to localize each mobile within the cell and to generate tracking ad...
Global optimization of a neural network-hidden Markov model hybrid
An original method for integrating artificial neural networks (ANN) with hidden Markov models (HMM) is proposed. ANNs are suitable for performing phonetic classification, wherea...
Effect of fading correlation on adaptive arrays in digital mobile radio
In this paper, we investigate the effect of correlations among the fading signals at the antenna elements of an adaptive array in a digital wireless communication system. With a...
Region competition: unifying snakes, region growing, energy/Bayes/MDL for multi-band image segmentation
We present a novel statistical and variational approach to image segmentation based on a new algorithm named region competition. This algorithm is derived by minimizing a genera...
Publication Info
- Year
- 2002
- Type
- article
- Citations
- 3913
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
3913
OpenAlex
Cite This
Martin Riedmiller,
Heinrich Braun
(2002).
A direct adaptive method for faster backpropagation learning: the RPROP algorithm.
IEEE International Conference on Neural Networks
.
https://doi.org/10.1109/icnn.1993.298623
Identifiers
- DOI
- 10.1109/icnn.1993.298623