Bidirectional Mamba state-space model for anomalous diffusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917864112390144 |
|---|---|
| author | Lavaud, Maxime Shokeeb, Yosef Lacherez, Juliette Amarouchene, Yacine Salez, Thomas |
| author_facet | Lavaud, Maxime Shokeeb, Yosef Lacherez, Juliette Amarouchene, Yacine Salez, Thomas |
| contents | Characterizing anomalous diffusion is crucial in order to understand the evolution of complex stochastic systems, from molecular interactions to cellular dynamics. In this work, we characterize the performances regarding such a task of Bi-Mamba, a novel state-space deep-learning architecture articulated with a bidirectional scan mechanism. Our implementation is tested on the AnDi-2 challenge datasets among others. Designed for regression tasks, the Bi-Mamba architecture infers efficiently the effective diffusion coefficient and anomalous exponent from single, short trajectories. As such, our results indicate the potential practical use of the Bi-Mamba architecture for anomalousdiffusion characterization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07299 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bidirectional Mamba state-space model for anomalous diffusion Lavaud, Maxime Shokeeb, Yosef Lacherez, Juliette Amarouchene, Yacine Salez, Thomas Soft Condensed Matter Biological Physics Optics Machine Learning Characterizing anomalous diffusion is crucial in order to understand the evolution of complex stochastic systems, from molecular interactions to cellular dynamics. In this work, we characterize the performances regarding such a task of Bi-Mamba, a novel state-space deep-learning architecture articulated with a bidirectional scan mechanism. Our implementation is tested on the AnDi-2 challenge datasets among others. Designed for regression tasks, the Bi-Mamba architecture infers efficiently the effective diffusion coefficient and anomalous exponent from single, short trajectories. As such, our results indicate the potential practical use of the Bi-Mamba architecture for anomalousdiffusion characterization. |
| title | Bidirectional Mamba state-space model for anomalous diffusion |
| topic | Soft Condensed Matter Biological Physics Optics Machine Learning |
| url | https://arxiv.org/abs/2412.07299 |