MetaCart Sign in to MyCiteSeerX

Include Citations | Advanced Search | Help

Disambiguated Search | Include Citations | Advanced Search | Help

RPROP - A Fast Adaptive Learning Algorithm (1992) [11 citations — 0 self]

by Martin Riedmiller ,  Heinrich Braun
Proc. of ISCIS VII), Universitat
Add To MetaCart

Abstract:

In this paper, a new learning algorithm, RPROP, is proposed. To overcome the inherent disadvantages of the pure gradient-descent technique of the original backpropagation procedure, RPROP performs an adaptation of the weight update-values according to the behaviour of the errorfunction. The results of RPROP on several learning tasks are shown in comparison to other well-known adaptive learning algorithms. 1 Introduction Backpropagation is the most widely used algorithm for supervised learning with multilayered feed-forward networks. The basic idea of the backpropagation learning algorithm is the repeated application of the chain rule to compute the influence of each weight in the network with respect to an arbitrary errorfunction E [1]: @E @w ij = @E @a i @a i @net i @net i @w ij (1) where w ij is the weight from neuron j to neuron i, a i is the activation value and net i is the weighted sum of the inputs of neuron i. Once the partial derivative for each weight is known, the a...

Citations

255 Increased Rates Of Convergence Through Learning Rate Adaptation – Jacobs - 1988
200 Parallel Distributed Processing – Rumelhart, McClelland - 1986
193 An empirical study of learning speed in back-propagation networks – Fahlman - 1988
47 Learning and Problem Solving with Multilayer Connectionist Systems – Anderson - 1986
44 SuperSAB: Fast Adaptive Backpropagation with good Scaling Properties – Tollenaere - 1990
8 Learning Strategies for Solving the Problem of Planning Using Backpropagation – Braun, Feulner, et al. - 1991
1 On Learning Strategies for Deterministic Games Using Backpropagation: A Case Study – Feulner, Ullrich