Sign-based learning schemes for pattern classification

Authors:
A. D. Anastasiadis;G. D. Magoulas;M. N. Vrahatis
Affiliations:
School of Computer Science and Information Systems, Birkbeck College, University of London, London Knowledge Lab, 23-29 Emerald Street, London WC1N 3QS, United Kingdom and School of Computer Scien ...;School of Computer Science and Information Systems, Birkbeck College, University of London, Malet Street, London WC1E 7HX, United Kingdom;Department of Mathematics, University of Patras Artificial Intelligence Research Center (UPAIRC), University of Patras, GR-26110 Patras, Greece
Venue:
Pattern Recognition Letters - Special issue: Artificial neural networks in pattern recognition
Year:
2005

Citing 12
Cited 2

Algorithm 666: Chabis: a mathematical software package for locating and evaluating roots of systems of nonlinear equations

ACM Transactions on Mathematical Software (TOMS)
Evolving neural networks

Biological Cybernetics
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
Deterministic global optimal FNN training algorithms

Neural Networks
Solving systems of nonlinear equations using the nonzero value of the topological degree

ACM Transactions on Mathematical Software (TOMS)
Effective backpropagation training with variable stepsize

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

Neural Computation
Optimal solution of nonlinear equations

Optimal solution of nonlinear equations
From linear to nonlinear iterative methods

Applied Numerical Mathematics
Simulated annealing and weight decay in adaptive learning: the SARPROP algorithm

IEEE Transactions on Neural Networks
Globally convergent algorithms with local learning rates

IEEE Transactions on Neural Networks

Improved sign-based learning algorithm derived by the composite nonlinear Jacobi process

Journal of Computational and Applied Mathematics - Special issue: The international conference on computational methods in sciences and engineering 2004
Self-scaled conjugate gradient training algorithms

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a new class of sign-based training algorithms for neural networks that combine the sign-based updates of the Rprop algorithm with the composite nonlinear Jacobi method. The theoretical foundations of the class are described and a heuristic Rprop-based Jacobi algorithm is empirically investigated through simulation experiments in benchmark pattern classification problems. Numerical evidence shows that this new modification of the Rprop algorithm exhibits improved learning speed in all cases tested, and compares favorably against the Rprop and a recently proposed modification, the improved Rprop.