University of Birmingham > Talks@bham > Theoretical Physics Seminars > The percolating cluster is invisible to image recognition with deep learning

## The percolating cluster is invisible to image recognition with deep learningAdd to your list(s) Download to your calendar using vCal - Djénabou Bayo, University of Warwick and CY Cergy Paris Universite
- Tuesday 27 June 2023, 13:15-14:30
- Theory Library.
If you have a question about this talk, please contact Dr Hannah Price. Note: **unusual day of the week** We study the two-dimensional site-percolation model on a square lattice. In this paradigmatic model, sites are randomly occupied with probability p; a second-order phase transition from a non-percolating to a fully percolating phase appears at occupation density pc, called percolation threshold. Through supervised deep learning approaches like classification and regression, we show that standard convolutional neural networks (CNNs), known to work well in similar image recognition tasks, can identify pc and indeed classify the states of a percolation lattice according to their p content or predict their p value via regression. When using instead of p the spatial cluster correlation length xi as labels, the recognition is beginning to falter. Finally, we show that the same network struggles to detect the presence of a spanning cluster. Rather, predictive power seems lost and the absence or presence of a global spanning cluster is not noticed by a CNN with local convolutional kernel. Since the existence of such a spanning cluster is at the heart of the percolation problem, our results suggest that CNNs require careful application when used in physics, particularly when encountering less-explored situations. This talk is part of the Theoretical Physics Seminars series. ## This talk is included in these lists:Note that ex-directory lists are not shown. |
## Other listsFeatured talks Featured lists http://talks.bham.ac.uk/show/index/1942## Other talksThe Holographic Universe TBA The Heat content of polygonal domains Parameter estimation for macroscopic pedestrian dynamics models using trajectory data EIC (Title TBC) Bases for permutation groups |