<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This 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.</p>
</abstract>

This 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.

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

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

This paper presents a parallel approach to the Levenberg-Marquardt algorithm (LM). The use of the Levenberg-Marquardt algorithm to train neural networks is...

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

Publié en ligne: 11 mars 2023

Pages: 45 - 61

Reçu: 19 oct. 2022

Accepté: 15 févr. 2023

DOI: https://doi.org/10.2478/jaiscr-2023-0006

Mots clés
feed-forward neural network, neural network learning algorithm, Levenberg-Marquardt algorithm, QR decomposition, Givens rotation

© 2023 Jarosław Bilski et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

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

Publié en ligne: 11 mars 2023

Pages: 45 - 61

Reçu: 19 oct. 2022

Accepté: 15 févr. 2023

DOI: https://doi.org/10.2478/jaiscr-2023-0006

Mots clésfeed-forward neural network, neural network learning algorithm, Levenberg-Marquardt algorithm, QR decomposition, Givens rotation

© 2023 Jarosław Bilski et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
feed-forward neural network, neural network learning algorithm, Levenberg-Marquardt algorithm, QR decomposition, Givens rotation