Application of the Givens Rotations in the Neural Network Learning Algorithm

Bilski, Jarosław; Kowalczyk, Bartosz; Żurada, Jacek M.

doi:10.1007/978-3-319-39378-0_5

Cited by 14 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since R is an upper triangle matrix, solving equation (17) is not too complex any more and results in obtaining the weight update vector ∆ (w(n)). In this paper the QR decomposition is accomplished by the Givens rotations as shown in [36]. The presented Levenberg-Marquardt algorithm can be summarized in the following steps:…”

Section: The Classic Levenberg-marquardt Algorithmmentioning

confidence: 99%

Local Levenberg-Marquardt Algorithm for Learning Feedforwad Neural Networks

Bilski

Kowalczyk

Marchlewska

et al. 2020

Journal of Artificial Intelligence and Soft Computing Research

Self Cite

View full text Add to dashboard Cite

This paper presents a local modification of the Levenberg-Marquardt algorithm (LM). First, the mathematical basics of the classic LM method are shown. The classic LM algorithm is very efficient for learning small neural networks. For bigger neural networks, whose computational complexity grows significantly, it makes this method practically inefficient. In order to overcome this limitation, local modification of the LM is introduced in this paper. The main goal of this paper is to develop a more complexity efficient modification of the LM method by using a local computation. The introduced modification has been tested on the following benchmarks: the function approximation and classification problems. The obtained results have been compared to the classic LM method performance. The paper shows that the local modification of the LM method significantly improves the algorithm’s performance for bigger networks. Several possible proposals for future works are suggested.

show abstract

Section: The Classic Levenberg-marquardt Algorithmmentioning

confidence: 99%