A modified levenberg marquardt algorithm for simultaneous learning of multiple datasets.
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 brief demonstrates the use of LM optimization algorithm when there are more than one dataset and o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2024
|
| Subjects: |
| _version_ | 1824452054970531840 |
|---|---|
| author | Önder Efe, Mehmet Kürkçü, Burak Kasnakoğlu, Coşku Mohamed, Zaharuddin Zhijie, Liu |
| author_facet | Önder Efe, Mehmet Kürkçü, Burak Kasnakoğlu, Coşku Mohamed, Zaharuddin Zhijie, Liu |
| author_sort | Önder Efe, Mehmet |
| collection | ePrints |
| description | 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 brief 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 brief. The results are verified on a regression problem. |
| first_indexed | 2025-02-19T02:44:26Z |
| format | Article |
| id | utm.eprints-108865 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2025-02-19T02:44:26Z |
| publishDate | 2024 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| record_format | dspace |
| spelling | utm.eprints-1088652025-01-07T07:41:05Z http://eprints.utm.my/108865/ A modified levenberg marquardt algorithm for simultaneous learning of multiple datasets. Önder Efe, Mehmet Kürkçü, Burak Kasnakoğlu, Coşku Mohamed, Zaharuddin Zhijie, Liu TK Electrical engineering. Electronics Nuclear engineering 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 brief 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 brief. The results are verified on a regression problem. Institute of Electrical and Electronics Engineers Inc. 2024-04 Article PeerReviewed Önder Efe, Mehmet and Kürkçü, Burak and Kasnakoğlu, Coşku and Mohamed, Zaharuddin and Zhijie, Liu (2024) A modified levenberg marquardt algorithm for simultaneous learning of multiple datasets. IEEE Transactions on Circuits and Systems II: Express Briefs, 71 (4). pp. 2379-2383. ISSN 1549-7747 http://dx.doi.org/10.1109/TCSII.2023.3335140 DOI:10.1109/TCSII.2023.3335140 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Önder Efe, Mehmet Kürkçü, Burak Kasnakoğlu, Coşku Mohamed, Zaharuddin Zhijie, Liu A modified levenberg marquardt algorithm for simultaneous learning of multiple datasets. |
| title | A modified levenberg marquardt algorithm for simultaneous learning of multiple datasets. |
| title_full | A modified levenberg marquardt algorithm for simultaneous learning of multiple datasets. |
| title_fullStr | A modified levenberg marquardt algorithm for simultaneous learning of multiple datasets. |
| title_full_unstemmed | A modified levenberg marquardt algorithm for simultaneous learning of multiple datasets. |
| title_short | A modified levenberg marquardt algorithm for simultaneous learning of multiple datasets. |
| title_sort | modified levenberg marquardt algorithm for simultaneous learning of multiple datasets |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| work_keys_str_mv | AT onderefemehmet amodifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets AT kurkcuburak amodifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets AT kasnakoglucosku amodifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets AT mohamedzaharuddin amodifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets AT zhijieliu amodifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets AT onderefemehmet modifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets AT kurkcuburak modifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets AT kasnakoglucosku modifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets AT mohamedzaharuddin modifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets AT zhijieliu modifiedlevenbergmarquardtalgorithmforsimultaneouslearningofmultipledatasets |