A global optimization algorithm based on novel interval analysis for training neural networks

Authors:
Hongru Li;Hailong Li;Yina Du
Affiliations:
Key Laboratory of Integrated Automation of Process Industry, Northeastern University, Ministry of Education, Shenyang, China;Key Laboratory of Integrated Automation of Process Industry, Northeastern University, Ministry of Education, Shenyang, China;Key Laboratory of Integrated Automation of Process Industry, Northeastern University, Ministry of Education, Shenyang, China
Venue:
ISICA'07 Proceedings of the 2nd international conference on Advances in computation and intelligence
Year:
2007

Citing 8
Cited 1

Global optimization over unbounded domains

SIAM Journal on Control and Optimization
An interval algorithm for constrained global optimization

ICCAM'92 Proceedings of the fifth international conference on Computational and applied mathematics
Interval extensions of non-smooth functions for global optimization and nonlinear systems solvers

Computing
An interval maximum entropy method for a discrete minimax problem

Applied Mathematics and Computation
A new multisection technique in interval methods for global optimization

Computing
Experiments with a new selection criterion in a fast interval optimization algorithm

Journal of Global Optimization
Training Product Unit Neural Networks with Genetic Algorithms

IEEE Expert: Intelligent Systems and Their Applications
Methods and Applications of Interval Analysis (SIAM Studies in Applied and Numerical Mathematics) (Siam Studies in Applied Mathematics, 2.)

Methods and Applications of Interval Analysis (SIAM Studies in Applied and Numerical Mathematics) (Siam Studies in Applied Mathematics, 2.)

Neural network output optimization using interval analysis

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A global optimal algorithm based on novel interval analysis was proposed for Feedforward neural networks (FNN). When FNN are trained with BP algorithm, there exists some local minimal points in error function, which make FNN training failed. In that case, interval analysis was took into FNN to work out the global minimal point. For interval FNN algorithm, an interval extension model was presented, which creates a narrower interval domain. And more, in the FNN training, hybrid strategy was employed in discard methods to accelerate the algorithm's convergence. In the proposed algorithm, the objective function gradient was utilized sufficiently to reduce the training time in both interval extension and discard methods procedure. At last, simulation experiments show the new interval FNN algorithm's availability.