An Optimization Methodology for Neural Network Weights and Architectures

Authors:
T. B. Ludermir;A. Yamazaki;C. Zanchettin
Affiliations:
Center of Informatics, Univ. Fed. de Pernambuco;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
2006

Citing 0
Cited 15

A New Adaptive Strategy for Pruning and Adding Hidden Neurons during Training Artificial Neural Networks

IDEAL '08 Proceedings of the 9th International Conference on Intelligent Data Engineering and Automated Learning
A linear ridgelet network

Neurocomputing
Design optimization of a spatial six degree-of-freedom parallel manipulator based on artificial intelligence approaches

Robotics and Computer-Integrated Manufacturing
A new adaptive merging and growing algorithm for designing artificial neural networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A new constructive algorithm for architectural and functional adaptation of artificial neural networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A meta-heuristic paradigm for solving the forward kinematics of 6-6 general parallel manipulator

CIRA'09 Proceedings of the 8th IEEE international conference on Computational intelligence in robotics and automation
Sensitivity versus accuracy in multiclass problems using memetic Pareto evolutionary neural networks

IEEE Transactions on Neural Networks
Direct search as unsupervised training algorithm for neural networks

ICS'10 Proceedings of the 14th WSEAS international conference on Systems: part of the 14th WSEAS CSCC multiconference - Volume II
Hybrid training of feed-forward neural networks with particle swarm optimization

ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
A hybrid neural network model based reinforcement learning agent

ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
An evolutionary constructive and pruning algorithm for artificial neural networks and its prediction applications

Neurocomputing
Performance evaluation of multilayer perceptrons for discriminating and quantifying multiple kinds of odors with an electronic nose

Neural Networks
PSO for reservoir computing optimization

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Optimization of the weights and asymmetric activation function family of neural network for time series forecasting

Expert Systems with Applications: An International Journal
Multi-step-ahead time series prediction using multiple-output support vector regression

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a methodology for neural network global optimization. The aim is the simultaneous optimization of multilayer perceptron (MLP) network weights and architectures, in order to generate topologies with few connections and high classification performance for any data sets. The approach combines the advantages of simulated annealing, tabu search and the backpropagation training algorithm in order to generate an automatic process for producing networks with high classification performance and low complexity. Experimental results obtained with four classification problems and one prediction problem has shown to be better than those obtained by the most commonly used optimization techniques