Thermodynamic Machine Learning through Maximum Work Production

06/27/2020
by   A. B. Boyd, et al.
0

Adaptive thermodynamic systems – such as a biological organism attempting to gain survival advantage, an autonomous robot performing a functional task, or a motor protein transporting intracellular nutrients – can improve their performance by effectively modeling the regularities and stochasticity in their environments. Analogously, but in a purely computational realm, machine learning algorithms seek to estimate models that capture predictable structure and identify irrelevant noise in training data by optimizing performance measures, such as a model's log-likelihood of having generated the data. Is there a sense in which these computational models are physically preferred? For adaptive physical systems we introduce the organizing principle that thermodynamic work is the most relevant performance measure of advantageously modeling an environment. Specifically, a physical agent's model determines how much useful work it can harvest from an environment. We show that when such agents maximize work production they also maximize their environmental model's log-likelihood, establishing an equivalence between thermodynamics and learning. In this way, work maximization appears as an organizing principle that underlies learning in adaptive thermodynamic systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/28/2020

Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models

Although with progress in introducing auxiliary amortized inference mode...
research
03/17/2022

On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks

Capturing aleatoric uncertainty is a critical part of many machine learn...
research
09/21/2020

A Survey on Machine Learning Applied to Dynamic Physical Systems

This survey is on recent advancements in the intersection of physical mo...
research
07/29/2019

An adaptive architecture for portability of greenhouse models

This work deals with the portability of greenhouse models, as we believe...
research
06/12/2023

Particularity

We describe a design principle for adaptive systems under which adaptati...
research
06/06/2022

Embrace the Gap: VAEs Perform Independent Mechanism Analysis

Variational autoencoders (VAEs) are a popular framework for modeling com...

Please sign up or login with your details

Forgot password? Click here to reset