Deep-Learning the Landscape
Author:
Preprint
Abstract
We propose a paradigm to deep-learn the ever-expanding databases which have emerged in mathematical physics and particle phenomenology, as diverse as the statistics of string vacua or combinatorial and algebraic geometry. As concrete examples, we establish multi-layer neural networks as both classifiers and predictors and train them with a host of available data ranging from Calabi-Yau manifolds and vector bundles, to quiver representations for gauge theories. We find that even a relatively simple neural network can learn many significant quantities to astounding accuracy in a matter of minutes and can also predict hithertofore unencountered results. This paradigm should prove a valuable tool in various investigations in landscapes in physics as well as pure mathematics.Keywords
All Related Versions
This publication has 45 references indexed in Scilit:
- Brane brick models in the mirrorJournal of High Energy Physics, 2017
- A Calabi-Yau database: threefolds constructed from the Kreuzer-Skarke listJournal of High Energy Physics, 2015
- On finiteness of type IIB compactifications: magnetized branes on elliptic Calabi-Yau threefoldsJournal of High Energy Physics, 2014
- A Comprehensive Scan for Heterotic SU(5) GUT modelsJournal of High Energy Physics, 2014
- Toric elliptic fibrations and F-theory compactificationsJournal of High Energy Physics, 2013
- Heterotic line bundle standard modelsJournal of High Energy Physics, 2012
- Brane tilings and reflexive polygonsFortschritte der Physik, 2012
- Heterotic models from vector bundles on toric Calabi-Yau manifoldsJournal of High Energy Physics, 2010
- New Calabi‐Yau manifolds with small Hodge numbersFortschritte der Physik, 2010
- On the classification of brane tilingsJournal of High Energy Physics, 2010