Exploring how deep learning decodes anomalous diffusion via Grad-CAM

TL;DR

This paper uses Grad-CAM to interpret how deep learning models recognize different anomalous diffusion mechanisms from raw data, revealing key features and improving robustness against noise.

Contribution

It demonstrates the application of Grad-CAM for explainability in deep learning-based classification of anomalous diffusion, uncovering the features used by the model.

Findings

Grad-CAM highlights trajectory segments crucial for classification.

Deep learning captures statistical features at multiple scales.

Robustness of the classifier improves with explainability insights.

Abstract

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.