Conference Paper/Proceeding/Abstract 653 views 66 downloads
Interpreting machine learning functions as physical observables
,
Dimitrios Bachtis,
Biagio Lucini
Proceedings of The 38th International Symposium on Lattice Field Theory — PoS(LATTICE2021), Volume: 396
Swansea University Authors:
Gert Aarts , Dimitrios Bachtis, Biagio Lucini
-
PDF | Version of Record
© Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0)
Download (931.23KB)
DOI (Published version): 10.22323/1.396.0248
Abstract
We propose to interpret machine learning functions as physical observables, opening up the possibility to apply “standard” statistical-mechanical methods to outputs from neural networks. This includes histogram reweighting and finite-size scaling, to analyse phase transitions quantitatively. In addi...
| Published in: | Proceedings of The 38th International Symposium on Lattice Field Theory — PoS(LATTICE2021) |
|---|---|
| ISSN: | 1824-8039 |
| Published: |
Trieste, Italy
Sissa Medialab
2022
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa60430 |
| Abstract: |
We propose to interpret machine learning functions as physical observables, opening up the possibility to apply “standard” statistical-mechanical methods to outputs from neural networks. This includes histogram reweighting and finite-size scaling, to analyse phase transitions quantitatively. In addition we incorporate predictive functions as conjugate variables coupled to an external field within the Hamiltonian of a system, allowing to induce order-disorder phase transitions in a novel manner. A noteworthy feature of this approach is that no knowledge of the symmetries in the Hamiltonian is required. |
|---|---|
| College: |
College of Science |
| Funders: |
ERC, STFC. Leverhulme Foundation, Royal Society, ERDF |