Drivetrain system identification in a multi-task learning strategy using partial asynchronous elastic averaging stochastic gradient descent
- Author
- Tom Staessens (UGent) and Guillaume Crevecoeur (UGent)
- Organization
- Project
- Abstract
- The limited ability of deep learning models to generalize to regions outside of the training data distribution impedes their use for mechatronic applications, with high requirements of safe and robust operation in multiple operating conditions. We draw inspiration from the fields of Multi-Task Learning and distributed computing and propose an adaptation to Elastic Averaging Stochastic Gradient Descent that makes it possible to leverage upon the information of a fleet of systems to extend the generalization capabilities of the individual models, without having access to the full dataset. We demonstrate in simulation that our method enables models to generalize even outside of the joint training data distribution of the fleet. We compare our method to vanilla Elastic Averaging Stochastic Gradient Descent and demonstrate the importance of our adaptation for convergence in the Multi-Task Learning setting. Finally we investigate the interplay between the elastic force and the individual gradients in the update rules as a determining force for its performance.
- Keywords
- Neural Network Generalization, System Identification, Mechatronics, Deep Learning, Wind Turbine, PROGNOSTICS
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 1.54 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8685867
- MLA
- Staessens, Tom, and Guillaume Crevecoeur. “Drivetrain System Identification in a Multi-Task Learning Strategy Using Partial Asynchronous Elastic Averaging Stochastic Gradient Descent.” 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), IEEE, 2020, pp. 1549–54, doi:10.1109/aim43001.2020.9158977.
- APA
- Staessens, T., & Crevecoeur, G. (2020). Drivetrain system identification in a multi-task learning strategy using partial asynchronous elastic averaging stochastic gradient descent. 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), 1549–1554. https://doi.org/10.1109/aim43001.2020.9158977
- Chicago author-date
- Staessens, Tom, and Guillaume Crevecoeur. 2020. “Drivetrain System Identification in a Multi-Task Learning Strategy Using Partial Asynchronous Elastic Averaging Stochastic Gradient Descent.” In 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), 1549–54. New York: IEEE. https://doi.org/10.1109/aim43001.2020.9158977.
- Chicago author-date (all authors)
- Staessens, Tom, and Guillaume Crevecoeur. 2020. “Drivetrain System Identification in a Multi-Task Learning Strategy Using Partial Asynchronous Elastic Averaging Stochastic Gradient Descent.” In 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), 1549–1554. New York: IEEE. doi:10.1109/aim43001.2020.9158977.
- Vancouver
- 1.Staessens T, Crevecoeur G. Drivetrain system identification in a multi-task learning strategy using partial asynchronous elastic averaging stochastic gradient descent. In: 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM). New York: IEEE; 2020. p. 1549–54.
- IEEE
- [1]T. Staessens and G. Crevecoeur, “Drivetrain system identification in a multi-task learning strategy using partial asynchronous elastic averaging stochastic gradient descent,” in 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Boston, MA, USA, 2020, pp. 1549–1554.
@inproceedings{8685867,
abstract = {{The limited ability of deep learning models to generalize to regions outside of the training data distribution impedes their use for mechatronic applications, with high requirements of safe and robust operation in multiple operating conditions. We draw inspiration from the fields of Multi-Task Learning and distributed computing and propose an adaptation to Elastic Averaging Stochastic Gradient Descent that makes it possible to leverage upon the information of a fleet of systems to extend the generalization capabilities of the individual models, without having access to the full dataset. We demonstrate in simulation that our method enables models to generalize even outside of the joint training data distribution of the fleet. We compare our method to vanilla Elastic Averaging Stochastic Gradient Descent and demonstrate the importance of our adaptation for convergence in the Multi-Task Learning setting. Finally we investigate the interplay between the elastic force and the individual gradients in the update rules as a determining force for its performance.}},
author = {{Staessens, Tom and Crevecoeur, Guillaume}},
booktitle = {{2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)}},
isbn = {{9781728167947}},
issn = {{2159-6255}},
keywords = {{Neural Network Generalization,System Identification,Mechatronics,Deep Learning,Wind Turbine,PROGNOSTICS}},
language = {{eng}},
location = {{Boston, MA, USA}},
pages = {{1549--1554}},
publisher = {{IEEE}},
title = {{Drivetrain system identification in a multi-task learning strategy using partial asynchronous elastic averaging stochastic gradient descent}},
url = {{http://doi.org/10.1109/aim43001.2020.9158977}},
year = {{2020}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: