Classification, inference and segmentation of anomalous diffusion with recurrent neural networks

DOI10.1088/1751-8121/ac070aOpenAlexW3171253577MaRDI QIDQ5874039

Giovanni Volpe, Stefano Bo, Aykut Argun

Publication date: 10 February 2023

Published in: Journal of Physics A: Mathematical and Theoretical (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1088/1751-8121/ac070a

zbMATH Keywords

anomalous diffusionrecurrent neural networksmachine learningchange point detectioninference and classification

Mathematics Subject Classification ID

Quantum theory (81-XX) Statistical mechanics, structure of matter (82-XX)

Related Items

Unsupervised learning of anomalous diffusion data: an anomaly detection approach ⋮ Efficient recurrent neural network methods for anomalously diffusing single particle short and noisy trajectories ⋮ Decomposing the effect of anomalous diffusion enables direct calculation of the Hurst exponent and model classification for single random paths ⋮ An empirical method to characterize displacement distribution functions for anomalous and transient diffusion ⋮ Deep learning-based parameter estimation of stochastic differential equations driven by fractional Brownian motions with measurement noise ⋮ Neural network-based parameter estimation of stochastic differential equations driven by Lévy noise ⋮ Characterization of anomalous diffusion classical statistics powered by deep learning (CONDOR) ⋮ WaveNet-based deep neural networks for the characterization of anomalous diffusion (WADNet) ⋮ Preface: characterisation of physical processes from anomalous diffusion data ⋮ Characterization of anomalous diffusion through convolutional transformers

Uses Software

• Keras
• Adam

Cites Work

• Analysis of short subdiffusive time series: scatter of the time-averaged mean-squared displacement
• Optimization Methods for Large-Scale Machine Learning
• Fractional Brownian Motions, Fractional Noises and Applications