Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Fast Computational Approach to the Levenberg-Marquardt Algorithm for Training Feedforward Neural Networks

Fast Computational Approach to the Levenberg-Marquardt Algorithm for Training Feedforward Neural... AbstractThis paper presents a parallel approach to the Levenberg-Marquardt algorithm (LM). The use of the Levenberg-Marquardt algorithm to train neural networks is associated with significant computational complexity, and thus computation time. As a result, when the neural network has a big number of weights, the algorithm becomes practically ineffective. This article presents a new parallel approach to the computations in Levenberg-Marquardt neural network learning algorithm. The proposed solution is based on vector instructions to effectively reduce the high computational time of this algorithm. The new approach was tested on several examples involving the problems of classification and function approximation, and next it was compared with a classical computational method. The article presents in detail the idea of parallel neural network computations and shows the obtained acceleration for different problems. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Artificial Intelligence and Soft Computing Research de Gruyter

Fast Computational Approach to the Levenberg-Marquardt Algorithm for Training Feedforward Neural Networks

Download PDF
17 pages

Loading next page...
 
/lp/de-gruyter/fast-computational-approach-to-the-levenberg-marquardt-algorithm-for-NoIxN2rHYF
Publisher
de Gruyter
Copyright
© 2023 Jarosław Bilski et al., published by Sciendo
eISSN
2083-2567
DOI
10.2478/jaiscr-2023-0006
Publisher site
See Article on Publisher Site

Abstract

AbstractThis paper presents a parallel approach to the Levenberg-Marquardt algorithm (LM). The use of the Levenberg-Marquardt algorithm to train neural networks is associated with significant computational complexity, and thus computation time. As a result, when the neural network has a big number of weights, the algorithm becomes practically ineffective. This article presents a new parallel approach to the computations in Levenberg-Marquardt neural network learning algorithm. The proposed solution is based on vector instructions to effectively reduce the high computational time of this algorithm. The new approach was tested on several examples involving the problems of classification and function approximation, and next it was compared with a classical computational method. The article presents in detail the idea of parallel neural network computations and shows the obtained acceleration for different problems.

Journal

Journal of Artificial Intelligence and Soft Computing Research – de Gruyter

Published: Mar 1, 2023

Keywords: feed-forward neural network; neural network learning algorithm; Levenberg-Marquardt algorithm; QR decomposition; Givens rotation

There are no references for this article.