Exploring how deep learning decodes anomalous diffusion via Grad-CAM
This work provides insights into explainable AI for anomalous diffusion classification, which is incremental as it applies an existing technique to a specific domain problem.
The study tackled the problem of understanding how deep learning classifies anomalous diffusion mechanisms by applying Grad-CAM to ResNets on raw trajectory data, revealing that it identifies crucial trajectory portions for robustness against noise and distills statistical features at different spatiotemporal scales.
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.