Santa Fe Institute Collaboration Platform

COMPLEX TIME: Adaptation, Aging, & Arrow of Time

Get Involved!
Contact: Caitlin Lorraine McShea, Program Manager, cmcshea@santafe.edu

A high-bias low-variance introduction to machine learning for physicists

From Complex Time
Revision as of 22:26, January 30, 2019 by RobertMarsland (talk | contribs) (Created page with "{{Reference Material |Meeting=Irreversible Processes in Ecological Evolution |Added by=RobertMarsland |title=A high-bias low-variance introduction to machine learning for phys...")

(diff) ← Older revision | Approved revision (diff) | Latest revision (diff) | Newer revision → (diff)
Category
General Reference
author-supplied keywords
keywords
authors
Pankaj Mehta
Ching-Hao Wang
Alexandre G. R. Day
Clint Richardson
title
A high-bias low-variance introduction to machine learning for physicists
year
2018


Abstract

Machine Learning (ML) is one of the most exciting and dynamic areas of modern research and application. The purpose of this review is to provide an introduction to the core concepts and tools of machine learning in a manner easily understood and intuitive to physicists. The review begins by covering fundamental concepts in ML and modern statistics such as the bias-variance tradeoff, overfitting, regularization, and generalization before moving on to more advanced topics in both supervised and unsupervised learning. Topics covered in the review include ensemble models, deep learning and neural networks, clustering and data visualization, energy-based models (including MaxEnt models and Restricted Boltzmann Machines), and variational methods. Throughout, we emphasize the many natural connections between ML and statistical physics. A notable aspect of the review is the use of Jupyter notebooks to introduce modern ML/statistical packages to readers using physics-inspired datasets (the Ising Model and Monte-Carlo simulations of supersymmetric decays of proton-proton collisions). We conclude with an extended outlook discussing possible uses of machine learning for furthering our understanding of the physical world as well as open problems in ML where physicists maybe able to contribute.

Counts

Citation count From Scopus. Refreshed every 5 days.
Page views
9

Identifiers

  • arxiv: 1803.08823

Related files

Add a file