309 citations · 788 across the 35 of their papers we have counts for
3 papers · 1 filter
Interpreting machine learning functions as physical observables
Gert Aarts, Dimitrios Bachtis, Biagio Lucini
We propose to interpret machine learning functions as physical observables, opening up the possibility to apply "standard" statistical-mechanical methods to outputs from neural net…
Ergodic sampling of the topological charge using the density of states
Guido Cossu, David Lancaster, Biagio Lucini +2
In lattice calculations, the approach to the continuum limit is hindered by the severe freezing of the topological charge, which prevents ergodic sampling in configuration space. I…
Quantum field-theoretic machine learning
Dimitrios Bachtis, Gert Aarts, Biagio Lucini
We derive machine learning algorithms from discretized Euclidean field theories, making inference and learning possible within dynamics described by quantum field theory. Specifica…