New globally convergent training scheme based on the resilient propagation algorithm

Authors:
Aristoklis D. Anastasiadis;George D. Magoulas;Michael N. Vrahatis
Affiliations:
School of Computer Science and Information Systems, Birkbeck College, University of London, Malet Street, London WC1E 7HX, UK;School of Computer Science and Information Systems, Birkbeck College, University of London, Malet Street, London WC1E 7HX, UK;Computational Intelligence Laboratory, Department of Mathematics, University of Patras Artificial Intelligence Research Center (UPAIRC), University of Patras, GR-26110 Patras, Greece
Venue:
Neurocomputing
Year:
2005

Citing 12
Cited 6

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
First- and second-order methods for learning: between steepest descent and Newton's method

Neural Computation
Original Contribution: A scaled conjugate gradient algorithm for fast supervised learning

Neural Networks
Effective backpropagation training with variable stepsize

Neural Networks
Improving the convergence of the backpropagation algorithm using learning rate adaptation methods

Neural Computation
A class of gradient unconstrained minimization algorithms with adaptive stepsize

Journal of Computational and Applied Mathematics
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Better Prediction of Protein Cellular Localization Sites with the it k Nearest Neighbors Classifier

Proceedings of the 5th International Conference on Intelligent Systems for Molecular Biology
From linear to nonlinear iterative methods

Applied Numerical Mathematics
Numerical Methods for Unconstrained Optimization and Nonlinear Equations (Classics in Applied Mathematics, 16)

Numerical Methods for Unconstrained Optimization and Nonlinear Equations (Classics in Applied Mathematics, 16)
Simulated annealing and weight decay in adaptive learning: the SARPROP algorithm

IEEE Transactions on Neural Networks
Training feedforward networks with the Marquardt algorithm

IEEE Transactions on Neural Networks

Universal parameter optimisation in games based on SPSA

Machine Learning
Variable step search algorithm for feedforward networks

Neurocomputing
Self-scaled conjugate gradient training algorithms

Neurocomputing
Study of neural net training methods in parallel and distributed architectures

Future Generation Computer Systems
Improved prediction of trans-membrane spans in proteins using an artificial neural network

CIBCB'09 Proceedings of the 6th Annual IEEE conference on Computational Intelligence in Bioinformatics and Computational Biology
Comparison of individual and combined ANN models for prediction of air and dew point temperature

Applied Intelligence

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, a new globally convergent modification of the Resilient Propagation-Rprop algorithm is presented. This new addition to the Rprop family of methods builds on a mathematical framework for the convergence analysis that ensures that the adaptive local learning rates of the Rprop's schedule generate a descent search direction at each iteration. Simulation results in six problems of the PROBEN1 benchmark collection show that the globally convergent modification of the Rprop algorithm exhibits improved learning speed, and compares favorably against the original Rprop and the Improved Rprop, a recently proposed Rrpop modification.