Koopman Learning with Episodic Memory
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916554093887488 |
|---|---|
| author | Redman, William T. Huang, Dean Fonoberova, Maria Mezić, Igor |
| author_facet | Redman, William T. Huang, Dean Fonoberova, Maria Mezić, Igor |
| contents | Koopman operator theory has found significant success in learning models of complex, real-world dynamical systems, enabling prediction and control. The greater interpretability and lower computational costs of these models, compared to traditional machine learning methodologies, make Koopman learning an especially appealing approach. Despite this, little work has been performed on endowing Koopman learning with the ability to leverage its own failures. To address this, we equip Koopman methods -- developed for predicting non-autonomous time-series -- with an episodic memory mechanism, enabling global recall of (or attention to) periods in time where similar dynamics previously occurred. We find that a basic implementation of Koopman learning with episodic memory leads to significant improvements in prediction on synthetic and real-world data. Our framework has considerable potential for expansion, allowing for future advances, and opens exciting new directions for Koopman learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_12615 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Koopman Learning with Episodic Memory Redman, William T. Huang, Dean Fonoberova, Maria Mezić, Igor Dynamical Systems Machine Learning Koopman operator theory has found significant success in learning models of complex, real-world dynamical systems, enabling prediction and control. The greater interpretability and lower computational costs of these models, compared to traditional machine learning methodologies, make Koopman learning an especially appealing approach. Despite this, little work has been performed on endowing Koopman learning with the ability to leverage its own failures. To address this, we equip Koopman methods -- developed for predicting non-autonomous time-series -- with an episodic memory mechanism, enabling global recall of (or attention to) periods in time where similar dynamics previously occurred. We find that a basic implementation of Koopman learning with episodic memory leads to significant improvements in prediction on synthetic and real-world data. Our framework has considerable potential for expansion, allowing for future advances, and opens exciting new directions for Koopman learning. |
| title | Koopman Learning with Episodic Memory |
| topic | Dynamical Systems Machine Learning |
| url | https://arxiv.org/abs/2311.12615 |