A hybrid algorithm for artificial neural network training

Authors:
Masoud Yaghini;Mohammad M. Khoshraftar;Mehdi Fallahi
Affiliations:
Rail Transportation Department, School of Railway Engineering, Iran University of Science and Technology, Resalat Sq. Hengam Street, Tehran, Iran;Rail Transportation Department, School of Railway Engineering, Iran University of Science and Technology, Resalat Sq. Hengam Street, Tehran, Iran;Rail Transportation Department, School of Railway Engineering, Iran University of Science and Technology, Resalat Sq. Hengam Street, Tehran, Iran
Venue:
Engineering Applications of Artificial Intelligence
Year:
2013

Citing 22
Cited 3

A quantitative study of experimental evaluations of neural network learning algorithms: current research practice

Neural Networks
Bayesian Network Classifiers

Machine Learning - Special issue on learning with probabilistic representations
Automatic early stopping using cross validation: quantifying the criteria

Neural Networks
Reliable classification using neural networks: a genetic algorithm and backpropagation comparison

Decision Support Systems
Alternative Neural Network Training Methods

IEEE Expert: Intelligent Systems and Their Applications
Training feed-forward neural networks with ant colony optimization: An application to pattern classification

HIS '05 Proceedings of the Fifth International Conference on Hybrid Intelligent Systems
Opposition-Based Learning: A New Scheme for Machine Intelligence

CIMCA '05 Proceedings of the International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce Vol-1 (CIMCA-IAWTIC'06) - Volume 01
An Analysis Of PSO Hybrid Algorithms For Feed-Forward Neural Networks Training

SBRN '06 Proceedings of the Ninth Brazilian Symposium on Neural Networks
Optimizing feedforward artificial neural network architecture

Engineering Applications of Artificial Intelligence
Particle Swarm Optimization of Neural Network Architectures andWeights

HIS '07 Proceedings of the 7th International Conference on Hybrid Intelligent Systems
A Novel Opposition-Based Particle Swarm Optimization for Noisy Problems

ICNC '07 Proceedings of the Third International Conference on Natural Computation - Volume 03
Letters: Evolving artificial neural networks using an improved PSO and DPSO

Neurocomputing
Artificial Bee Colony (ABC) Optimization Algorithm for Training Feed-Forward Neural Networks

MDAI '07 Proceedings of the 4th international conference on Modeling Decisions for Artificial Intelligence
Evolutionary Artificial Neural Network Design and Training for wood veneer classification

Engineering Applications of Artificial Intelligence
A new adaptive merging and growing algorithm for designing artificial neural networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Evolutionary artificial neural networks by multi-dimensional particle swarm optimization

Neural Networks
Particle Swarm Optimization and Intelligence: Advances and Applications

Particle Swarm Optimization and Intelligence: Advances and Applications
The particle swarm - explosion, stability, and convergence in amultidimensional complex space

IEEE Transactions on Evolutionary Computation
Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients

IEEE Transactions on Evolutionary Computation
An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Simulated annealing and weight decay in adaptive learning: the SARPROP algorithm

IEEE Transactions on Neural Networks
Training neural nets with the reactive tabu search

IEEE Transactions on Neural Networks

DE+RBFNs based classification: A special attention to removal of inconsistency and irrelevant features

Engineering Applications of Artificial Intelligence
Particle swarm optimization with increasing topology connectivity

Engineering Applications of Artificial Intelligence
Survey A review of opposition-based learning from 2005 to 2012

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Artificial neural network (ANN) training is one of the major challenges in using a prediction model based on ANN. Gradient based algorithms are the most frequent training algorithms with several drawbacks. The aim of this paper is to present a method for training ANN. The ability of metaheuristics and greedy gradient based algorithms are combined to obtain a hybrid improved opposition based particle swarm optimization and a back propagation algorithm with the momentum term. Opposition based learning and random perturbation help population diversification during the iteration. Use of time-varying parameter improves the search ability of standard PSO, and constriction factor guarantees particles convergence. Since several contingent local minima conditions may happen in the weight space, a new cross validation method is proposed to prevent overfitting. Effectiveness and efficiency of the proposed method are compared with several other famous ANN training algorithms on the various benchmark problems.