TherML: Thermodynamics of Machine Learning. Alemi, A. A. & Fischer, I.
TherML: Thermodynamics of Machine Learning [link]Paper  abstract   bibtex   
In this work we offer a framework for reasoning about a wide class of existing objectives in machine learning. We develop a formal correspondence between this work and thermodynamics and discuss its implications.
@article{alemiTherMLThermodynamicsMachine2018,
  archivePrefix = {arXiv},
  eprinttype = {arxiv},
  eprint = {1807.04162},
  primaryClass = {cond-mat, stat},
  title = {{{TherML}}: {{Thermodynamics}} of {{Machine Learning}}},
  url = {http://arxiv.org/abs/1807.04162},
  shorttitle = {{{TherML}}},
  abstract = {In this work we offer a framework for reasoning about a wide class of existing objectives in machine learning. We develop a formal correspondence between this work and thermodynamics and discuss its implications.},
  urldate = {2019-05-22},
  date = {2018-07-11},
  keywords = {Statistics - Machine Learning,Condensed Matter - Statistical Mechanics,Computer Science - Machine Learning},
  author = {Alemi, Alexander A. and Fischer, Ian},
  file = {/home/dimitri/Nextcloud/Zotero/storage/XQJKMW9R/Alemi and Fischer - 2018 - TherML Thermodynamics of Machine Learning.pdf;/home/dimitri/Nextcloud/Zotero/storage/4B76X7GC/1807.html}
}

Downloads: 0