Exploring Various Sequential Learning Methods for Deformation History Modeling
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913777799135232 |
|---|---|
| author | Yatkin, Muhammed Adil Korgesaar, Mihkel Romanoff, Jani Islak, Umit Kurban, Hasan |
| author_facet | Yatkin, Muhammed Adil Korgesaar, Mihkel Romanoff, Jani Islak, Umit Kurban, Hasan |
| contents | Current neural network (NN) models can learn patterns from data points with historical dependence. Specifically, in natural language processing (NLP), sequential learning has transitioned from recurrence-based architectures to transformer-based architectures. However, it is unknown which NN architectures will perform the best on datasets containing deformation history due to mechanical loading. Thus, this study ascertains the appropriateness of 1D-convolutional, recurrent, and transformer-based architectures for predicting deformation localization based on the earlier states in the form of deformation history. Following this investigation, the crucial incompatibility issues between the mathematical computation of the prediction process in the best-performing NN architectures and the actual values derived from the natural physical properties of the deformation paths are examined in detail. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03818 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Various Sequential Learning Methods for Deformation History Modeling Yatkin, Muhammed Adil Korgesaar, Mihkel Romanoff, Jani Islak, Umit Kurban, Hasan Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Current neural network (NN) models can learn patterns from data points with historical dependence. Specifically, in natural language processing (NLP), sequential learning has transitioned from recurrence-based architectures to transformer-based architectures. However, it is unknown which NN architectures will perform the best on datasets containing deformation history due to mechanical loading. Thus, this study ascertains the appropriateness of 1D-convolutional, recurrent, and transformer-based architectures for predicting deformation localization based on the earlier states in the form of deformation history. Following this investigation, the crucial incompatibility issues between the mathematical computation of the prediction process in the best-performing NN architectures and the actual values derived from the natural physical properties of the deformation paths are examined in detail. |
| title | Exploring Various Sequential Learning Methods for Deformation History Modeling |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2504.03818 |