Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bae, Jaeyong, Baek, Yongjoo, Jeong, Hawoong
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2410.16345
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910659910828032
author Bae, Jaeyong
Baek, Yongjoo
Jeong, Hawoong
author_facet Bae, Jaeyong
Baek, Yongjoo
Jeong, Hawoong
contents While deep learning has been successfully applied to the data-driven classification of anomalous diffusion mechanisms, how the algorithm achieves the feat still remains a mystery. In this study, we use a well-known technique aimed at achieving explainable AI, namely the Gradient-weighted Class Activation Map (Grad-CAM), to investigate how deep learning (implemented by ResNets) recognizes the distinctive features of a particular anomalous diffusion model from the raw trajectory data. Our results show that Grad-CAM reveals the portions of the trajectory that hold crucial information about the underlying mechanism of anomalous diffusion, which can be utilized to enhance the robustness of the trained classifier against the measurement noise. Moreover, we observe that deep learning distills unique statistical characteristics of different diffusion mechanisms at various spatiotemporal scales, with larger-scale (smaller-scale) features identified at higher (lower) layers.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16345
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring how deep learning decodes anomalous diffusion via Grad-CAM
Bae, Jaeyong
Baek, Yongjoo
Jeong, Hawoong
Machine Learning
Data Analysis, Statistics and Probability
While deep learning has been successfully applied to the data-driven classification of anomalous diffusion mechanisms, how the algorithm achieves the feat still remains a mystery. In this study, we use a well-known technique aimed at achieving explainable AI, namely the Gradient-weighted Class Activation Map (Grad-CAM), to investigate how deep learning (implemented by ResNets) recognizes the distinctive features of a particular anomalous diffusion model from the raw trajectory data. Our results show that Grad-CAM reveals the portions of the trajectory that hold crucial information about the underlying mechanism of anomalous diffusion, which can be utilized to enhance the robustness of the trained classifier against the measurement noise. Moreover, we observe that deep learning distills unique statistical characteristics of different diffusion mechanisms at various spatiotemporal scales, with larger-scale (smaller-scale) features identified at higher (lower) layers.
title Exploring how deep learning decodes anomalous diffusion via Grad-CAM
topic Machine Learning
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2410.16345