Poli, Riccardo and Yilmaz, Ahmet (2023) Incorrect Application of Yilmaz–Poli (2022) Initialisation Method in dePater–Mitici 2023 paper entitled “A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers”. Neural Networks, 168. pp. 57-58. DOI https://doi.org/10.1016/j.neunet.2023.09.017
Poli, Riccardo and Yilmaz, Ahmet (2023) Incorrect Application of Yilmaz–Poli (2022) Initialisation Method in dePater–Mitici 2023 paper entitled “A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers”. Neural Networks, 168. pp. 57-58. DOI https://doi.org/10.1016/j.neunet.2023.09.017
Poli, Riccardo and Yilmaz, Ahmet (2023) Incorrect Application of Yilmaz–Poli (2022) Initialisation Method in dePater–Mitici 2023 paper entitled “A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers”. Neural Networks, 168. pp. 57-58. DOI https://doi.org/10.1016/j.neunet.2023.09.017
Abstract
In this letter to the editor we report on a methodological error made in the article entitled “A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers” by dePater and Mitici recently appeared in this journal. The error relates to the incorrect application of a weight initialisation method we derived, published last year in this same journal.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Mathematics; Neural Networks, Computer |
| Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
| SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
| Depositing User: | Unnamed user with email elements@essex.ac.uk |
| Date Deposited: | 12 Jan 2026 11:32 |
| Last Modified: | 12 Jan 2026 11:32 |
| URI: | http://repository.essex.ac.uk/id/eprint/37400 |
Available files
Filename: letter_to_editor.pdf