A novel fast feedforward neural networks training algorithm
Authors:
- Jerzy Bilski,
- Bartosz Kowalczyk,
- Andrzej Marjański,
- Michał Gandor,
- Jacek Zurada
Abstract
In this paper a new neural networks training algorithm is presented. The algorithm originates from the Recursive Least Squares (RLS) method commonly used in adaptive filtering. It uses the QR decomposition in conjunction with the Givens rotations for solving a normal equation - resulting from minimization of the loss function. An important parameter in neural networks is training time. Many commonly used algorithms require a big number of iterations in order to achieve a satisfactory outcome while other algorithms are effective only for small neural networks. The proposed solution is characterized by a very short convergence time compared to the well-known backpropagation method and its variants. The paper contains a complete mathematical derivation of the proposed algorithm. There are presented extensive simulation results using various benchmarks including function approximation, classification, encoder, and parity problems. Obtained results show the advantages of the featured algorithm which outperforms commonly used recent state-of-the-art neural networks training algorithms, including the Adam optimizer and the Nesterov’s accelerated gradient.
- Record ID
- CUTe81ea207cffb4b9eb0f86fea3e1b9f77
- Publication categories
- ;
- Author
- Journal series
- Journal of Artificial Intelligence and Soft Computing Research, ISSN 2083-2567, e-ISSN 2449-6499
- Issue year
- 2021
- Vol
- 11
- No
- 4
- Pages
- 287-306
- Other elements of collation
- rys.; tab.; wykr.; Bibliografia (na s.) - 303-305; Bibliografia (liczba pozycji) - 38; Oznaczenie streszczenia - Abstr.; Numeracja w czasopiśmie - Vol. 11, No. 4
- Keywords in English
- neural network training algorithm, QR decomposition, Givens rotations, approximation, classification
- DOI
- DOI:10.2478/jaiscr-2021-0017 Opening in a new tab
- URL
- https://sciendo.com/article/10.2478/jaiscr-2021-0017 Opening in a new tab
- Language
- eng (en) English
- License
- Score (nominal)
- 140
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUTe81ea207cffb4b9eb0f86fea3e1b9f77/
- URN
urn:pkr-prod:CUTe81ea207cffb4b9eb0f86fea3e1b9f77
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.