mlsanityData to 14 Oct 2026

Exploring how deep learning decodes anomalous diffusion via Grad-CAM

arXiv 2410.16345 ↗First posted 21 Oct 2024cs.LG physics.data-ancited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 61 references that are in the map. First posted on arXiv 21 Oct 2024.

Builds on

17 of 61 references.

References · 17

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  8. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  9. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  10. 2018A high-bias, low-variance introduction to Machine Learning for physicistscited by 108
  11. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  12. 2023A Review of Deep Learning Techniques for Speech Processingcited by 52
5 more
  1. 2022Geometric deep learning reveals the spatiotemporal fingerprint of microscopic motioncited by 15
  2. 2018Robust Tumor Localization with Pyramid Grad-CAMcited by 13
  3. 2022Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4mlcited by 11
  4. 2019Machine learning method for single trajectory characterizationcited by 8
  5. 2021Efficient recurrent neural network methods for anomalously diffusing single particle short and noisy trajectoriescited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021WaveNet-Based Deep Neural Networks for the Characterization of Anomalous Diffusion (WADNet)
  2. 2021Extreme Learning Machine for the Characterization of Anomalous Diffusion from Single Trajectories (AnDi-ELM)
  3. 2021Unsupervised learning of anomalous diffusion data
  4. 2026Grokking of Diffusion Models: Case Study on Modular Addition
  5. 2024Bidirectional Mamba state-space model for anomalous diffusion
  6. 2024Physics Informed Distillation for Diffusion Models
  7. 2025Are We Really Learning the Score Function? Reinterpreting Diffusion Models Through Wasserstein Gradient Flow Matching
  8. 2023Generalised Scale-Space Properties for Probabilistic Diffusion Models