TherML: Thermodynamics of Machine Learning

07/11/2018

∙

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.

READ FULL TEXT

TherML: Thermodynamics of Machine Learning

A Machine-Learning Framework for Design for Manufacturability

Fano schemes of generic intersections and machine learning

Confounder Selection: Objectives and Approaches

Limit Cycles of AdaBoost

Machine Learning Fund Categorizations

A machine-learning software-systems approach to capture social, regulatory, governance, and climate problems

Semi-Lexical Languages – A Formal Basis for Unifying Machine Learning and Symbolic Reasoning in Computer Vision

TherML: Thermodynamics of Machine Learning

Related Research

A Machine-Learning Framework for Design for Manufacturability

Fano schemes of generic intersections and machine learning

Confounder Selection: Objectives and Approaches

Limit Cycles of AdaBoost

Machine Learning Fund Categorizations

A machine-learning software-systems approach to capture social, regulatory, governance, and climate problems

Semi-Lexical Languages – A Formal Basis for Unifying Machine Learning and Symbolic Reasoning in Computer Vision