Improving generalization of MLPs with sliding mode control and the Levenberg-Marquardt algorithm

Authors:
Marcelo Azevedo Costa;Antônio de Pádua Braga;Benjamin Rodrigues de Menezes
Affiliations:
Department of Statistics, Federal University of Minas Gerais, Belo Horizonte, MG, Brazil;Department of Electronics Engineering, Federal University of Minas Gerais, Belo Horizonte, MG, Brazil;Department of Electronics Engineering, Federal University of Minas Gerais, Belo Horizonte, MG, Brazil
Venue:
Neurocomputing
Year:
2007

Citing 3
Cited 6

Neural networks and the bias/variance dilemma

Neural Computation
Pruning algorithms-a survey

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

IEEE Transactions on Neural Networks

Evolutionary product-unit neural networks classifiers

Neurocomputing
Gradient descent decomposition for multi-objective learning

IDEAL'11 Proceedings of the 12th international conference on Intelligent data engineering and automated learning
Ensemble forecasting of Value at Risk via Multi Resolution Analysis based methodology in metals markets

Expert Systems with Applications: An International Journal
Convergence analysis of sliding mode trajectories in multi-objective neural networks learning

Neural Networks
Application of learning pallets for real-time scheduling by the use of radial basis function network

Neurocomputing
A computational geometry approach for pareto-optimal selection of neural networks

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II

Quantified Score

Hi-index	0.01

Visualization

Abstract

A variation of the well-known Levenberg-Marquardt for training neural networks is proposed in this work. The algorithm presented restricts the norm of the weights vector to a preestablished norm value and finds the minimum error solution for that norm value. The norm constrain controls the neural networks degree of freedom. The more the norm increases, the more flexible is the neural model. Therefore, more fitted to the training set. A range of different norm solutions is generated and the best generalization solution is selected according to the validation set error. The results show the efficiency of the algorithm in terms of generalization performance.