C. Igel and M. H usken, "Improving the Rprop Learning Algorithm," in Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Evolutionary Optimization for Problem Classes with.. - Hüsken, Sendhoff (2000) (Correct)
....weights and topology are encoded with a direct encoding scheme. The mutations of the individuals are close to the suggestions in [8] i.e. insertion deletion of connections hidden neurons, no crossover) Learning is performed using iRprop , an improved version of the RpropLearning algorithm [10], for 300 learning cycles. To avoid over fitting, learning is combined with crossvalidation. In case of the Ensemble Method the EP Tournament Selection [11] is used and due to the evolution in changing environment in case of the Generation Method, we employ the non elitistic ( #) selection. 3 ....
C. Igel and M. Husken. Improving the rprop learning algorithm. In Proceedings of the Second International ICSC Symposium on Neural Computation, pages 115--121. ICSC Academic Press, 2000.
Optimization for Problem Classes - Neural Networks that.. - Hüsken, Gayko, Sendhoff (2000) (Correct)
....of the succeeding generation are chosen us ing the EP tournament selection (Fogel 1995) In Section 4.5 we utilize the ( #) selection, since an elitistic selection is not applicable. The fitness of an individual mainly depends on the error after a period of learning. The iRprop Algorithm (Igel and Hsken 2000), an improved version of the Rprop Algorithm (Riedmiller 1994) is employed to minimize the mean squared error e = 1 P # P p=1 (y p y p ) 2 . Here, P denotes the number of data points presented and y p and y p denote the ANN s output and the target value for each data point p. To avoid ....
Igel, C. and M. Hsken (2000). Improving the rprop learning algorithm.
Rprop Using the Natural Gradient - Igel, al. (2005) Self-citation (Igel) (Correct)
No context found.
C. Igel and M. Husken. Improving the Rprop learning algorithm. In H. Bothe and R. Rojas, editors, Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
Recurrent Neural Networks for Time Series Classification - Hüsken, Stagge (2003) Self-citation (Husken) (Correct)
No context found.
C. Igel and M. Husken. Improving the Rprop learning algorithm. In H.-H. Bothe and R. Rojas, editors, Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
Empirical Evaluation of the Improved Rprop Learning Algorithms - Igel, Hüsken (2003) (2 citations) Self-citation (Igel Husken) (Correct)
No context found.
C. Igel and M. Husken. Improving the Rprop learning algorithm. In H. Bothe and R. Rojas, editors, Proceedings of the Second International Symposium on Neural Computation, NC 2000.
Statistics and Time Series Analyses of BTA Deep Hole.. - Weinert, Webbe, Hüsken.. (2001) Self-citation (Husken) (Correct)
....stable or not by means of the threshold method previously described. Furthermore, to improve the network s performance, also the states up to 0.5 s prior to the transition found so far are marked as chatter. Data stemming from 5 di#erent drilling processes and the iRprop learning algorithm [2] are used for training the network s weights (i.e. minimizing the mean squared di#erence between the network s output and the target values) Another 5 drilling processes are used to test the generalization ability of the trained network. To improve the stability of the classification based on ....
C. Igel and M. Husken. Improving the Rprop learning algorithm. In H.-H. Bothe and R. Rojas, editors, Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
Task-Dependent Evolution of Modularity in Neural Networks .. - Hüsken, Igel, Toussaint (2001) Self-citation (Igel Hiisken) (Correct)
....to cope with a class of problems, i.e. to be able to adapt to a number of different, but related problems, in particular within a short time. The modularity may be one of the main differences between the ANNs evolved in [8] for the two different tasks. Training is performed by means of iRprop [9], an improved version of the Rprop Algorithm [12] which is a powerful, gradient based learning algorithm for neural networks. The aim of training is the minimization of the mean squared error E (mse) i.e. the mean squared difference between the network s outputs j and the target values yj) We ....
C. Igel and M. Hiisken. Improving the Rprop learning algorithm. In H.-H. Bothe and R. Rojas, editors, Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
Time Series Prediction with Ensemble Models - Wichard, Ogorzalek (2004) (2 citations) (Correct)
No context found.
C. Igel and M. H usken, "Improving the Rprop Learning Algorithm," in Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
The Fourth International Workshop - On Knowledge Discovery (2006) (Correct)
No context found.
Christian Igel and Michael Husken. Improving the Rprop Learning Algorithm. In Proceedings of the Second International ICSC Symposium on Neural Computation, pages 115--121, Berlin, 2000. ICSC Academic Press.
Building Ensembles with Heterogeneous Models - Wichard, Merkwirth, Ogorzalek (2003) (Correct)
No context found.
Igel, C., Husken, M.: Improving the Rprop Learning Algorithm. In: Bothe, H., Rojas, R. (eds.): Proceedings of the Second International ICSC Symposium on Neural Computation. ICSC Academic Press, Berlin (2000) 115--121
Model Selection in an Ensemble Framework - Wichard (2006) (Correct)
No context found.
C. Igel and M. H usken, "Improving the Rprop learning algorithm," in Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
Computational Intelligence Methods for Financial Forecasting - Pavlidis, al. (2005) (Correct)
No context found.
C. Igel and M. Husken, Improving the Rprop learning algorithm, Proceedings of the Second International ICSC Symposium on Neural Computation (NC
Determining the Number of Real Roots of Polynomials through.. - Mourrain, al. (2006) (Correct)
No context found.
C. Igel and M. Husken, Improving the Rprop learning algorithm, In Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000), (Edited by H. Bothe and R. Rojas), pp. 115--121, ICSC Academic Press, (2000).
Financial Forecasting through Unsupervised.. - Pavlidis.. (2006) (Correct)
No context found.
C. Igel and M. Husken, Improving the Rprop learning algorithm, Proceedings of the Second International ICSC Symposium on Neural Computation (NC
Time Series Forecasting Methodology for.. - Pavlidis, Tasoulis.. (2005) (Correct)
No context found.
C. Igel and M. H usken, Improving the Rprop learning algorithm, Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
Tumor Detection In Colonoscopy - Using The Unsupervised (Correct)
No context found.
Christian Igel and Michael Husken. Improving the Rprop learning algorithm. In H. Bothe and R. Rojas, editors, Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
Dynamic Search Trajectory Methods for Neural - Network Training Petalas (Correct)
No context found.
Igel, C., Husken, M.: Improving the Rprop learning algorithm. In Bothe, H., Rojas, R., eds.: Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000), ICSC Academic Press (2000) 115--121
Online Neural Network Training for Automatic - Ischemia Episode Detection (Correct)
No context found.
Igel, C., Husken, M.: Improving the Rprop learning algorithm. In Bothe, H., Rojas, R., eds.: Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000), ICSC Academic Press (2000) 115--121 D.K. Tasoulis et al.
Tumor Detection In Colonoscopy - Using The Unsupervised (2004) (Correct)
No context found.
Christian Igel and Michael Husken. Improving the Rprop learning algorithm. In H. Bothe and R. Rojas, editors, Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
Time Series Forecasting Methodology for.. - Pavlidis, Tasoulis.. (2004) (Correct)
No context found.
C. Igel and M. H usken, Improving the Rprop learning algorithm, Proceedings of the Second International ICSC Symposium on Neural Computation (NC 2000.
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