Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/10999
Title: A Modified Levenberg Marquardt Algorithm for Simultaneous Learning of Multiple Datasets
Authors: Efe, M.O.
Kurkcu, B.
Kasnakoglu, C.
Mohamed, Z.
Liu, Z.
Keywords: Artificial neural networks; Biological neural networks; Jacobian matrices; Levenberg-Marquardt Algorithm; Masked Neural Networks; Multiple Dataset Learning; Neurons; Optimization; Training; Tuning
Bioinformatics; DNA; Jacobian matrices; Learning algorithms; Parameter estimation; Best paths; Biological neural networks; Levenberg-Marquardt algorithm; Masked neural network; Multiple data sets; Multiple dataset learning; Neural-networks; Optimisations; Training dataset; Tuning; Neural networks
Issue Date: 2023
Publisher: Institute of Electrical and Electronics Engineers Inc.
Abstract: Levenberg-Marquardt (LM) algorithm is a powerful approach to optimize the parameters of a neural network (NN). Given a training dataset, the algorithm synthesizes the best path toward the optimum. This paper demonstrates the use of LM optimization algorithm when there are more than one dataset and on/off type switching of NN parameters is allowed. For each dataset a pre-selected set of parameters are allowed for modification and the proposed scheme reformulates the Jacobian under the switching mechanism. The results show that a NN can store information available in different datasets by a simple modification to the original LM algorithm, which is the novelty introduced in this study. The results are verified on a regression problem. IEEE
URI: https://doi.org/10.1109/TCSII.2023.3335140
https://hdl.handle.net/20.500.11851/10999
ISSN: 1549-7747
Appears in Collections:Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Show full item record



CORE Recommender

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.