English
Related papers

Related papers: Thermodynamic Machine Learning through Maximum Wor…

200 papers

A Boltzmann machine is a stochastic neural network that has been extensively used in the layers of deep architectures for modern machine learning applications. In this paper, we develop a Boltzmann machine that is capable of modelling…

Statistical Mechanics · Physics 2016-10-18 Giacomo Torlai , Roger G. Melko

This work studies the general principles of improving the learning of language models (LMs), which aims at reducing the necessary training steps for achieving superior performance. Specifically, we present a theory for the optimal learning…

Computation and Language · Computer Science 2024-03-05 Yuxian Gu , Li Dong , Yaru Hao , Qingxiu Dong , Minlie Huang , Furu Wei

Many organisms capitalize on their ability to predict the environment to maximize available free energy, and reinvest this energy to create new complex structures. This functionality relies on the manipulation of patterns - temporally…

Quantum Physics · Physics 2017-04-27 Andrew J. P. Garner , Jayne Thompson , Vlatko Vedral , Mile Gu

Recent work emphasizes that the maximum entropy principle provides a bridge between statistical mechanics models for collective behavior in neural networks and experiments on networks of real neurons. Most of this work has focused on…

Neurons and Cognition · Quantitative Biology 2015-06-05 Gasper Tkacik , Olivier Marre , Thierry Mora , Dario Amodei , Michael J. Berry , William Bialek

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

Machine Learning · Computer Science 2020-12-29 Shuang Li , Shuai Xiao , Shixiang Zhu , Nan Du , Yao Xie , Le Song

We propose and analyze a process that extracts useful work from a single active particle maintained at constant temperature in a harmonic potential by measuring the relative sign of the self-propulsion and the confining force and then…

Statistical Mechanics · Physics 2026-03-09 Grzegorz Szamel

Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…

Machine Learning · Computer Science 2020-08-12 Suraj Nair , Silvio Savarese , Chelsea Finn

We show how to adjust the parameters of a thermodynamic computer by gradient descent in order to perform a desired computation at a specified observation time. Within a digital simulation of a thermodynamic computer, training proceeds by…

Statistical Mechanics · Physics 2025-09-22 Stephen Whitelam

In quantum systems which satisfy the hypothesis of equal weights for eigenstates [4], the maximum work principle (for extremely slow and relatively fast operation) is derived by using quantum dynamics alone. This may be a crucial step in…

Statistical Mechanics · Physics 2007-05-23 Hal Tasaki

We have formulated a family of machine learning problems as the time evolution of Parametric Probabilistic Models (PPMs), inherently rendering a thermodynamic process. Our primary motivation is to leverage the rich toolbox of thermodynamics…

Machine Learning · Computer Science 2024-01-31 Shervin Sadat Parsi

A thermodynamically motivated neural network model is described that self-organizes to transport charge associated with internal and external potentials while in contact with a thermal reservoir. The model integrates techniques for rapid,…

Neurons and Cognition · Quantitative Biology 2020-04-22 Todd Hylton

Data-driven, machine learning (ML) models of atomistic interactions are often based on flexible and non-physical functions that can relate nuanced aspects of atomic arrangements into predictions of energies and forces. As a result, these…

Materials Science · Physics 2024-05-15 Bartosz Barzdajn , Christopher P. Race

After the justification of the maximum entropy approach for equilibrium thermodynamic system, and of a maximum path entropy algorithm for nonequilibrium thermodynamic systems by virtue of the principle of virtual work, we present in this…

Statistical Mechanics · Physics 2007-12-18 Qiuping A. Wang

Machine learning has been increasingly applied in climate modeling on system emulation acceleration, data-driven parameter inference, forecasting, and knowledge discovery, addressing challenges such as physical consistency, multi-scale…

Imitation learning enables robots to learn from demonstrations. Previous imitation learning algorithms usually assume access to optimal expert demonstrations. However, in many real-world applications, this assumption is limiting. Most…

Machine Learning · Computer Science 2021-03-11 Zhangjie Cao , Dorsa Sadigh

The prediction of future climate scenarios under anthropogenic forcing is critical to understand climate change and to assess the impact of potentially counter-acting technologies. Machine learning and hybrid techniques for this prediction…

Machine Learning · Computer Science 2021-12-02 Sebastian Hoffmann , Christian Lessig

The metabolic processes complexity is at the heart of energy conversion in living organisms and forms a huge obstacle to develop tractable thermodynamic metabolism models. By raising our analysis to a higher level of abstraction, we develop…

Statistical Mechanics · Physics 2020-06-02 C. Goupil , H. Ouerdane , E. Herbert , Y. D'Angelo , C. Goupil

This tutorial investigates the convergence of statistical mechanics and learning theory, elucidating the potential enhancements in machine learning methodologies through the integration of foundational principles from physics. The tutorial…

Machine Learning · Computer Science 2024-11-26 Star , Liu

We develop the laws of thermodynamics in terms of general exponential families. By casting learning (log-loss minimization) problems in max-entropy and statistical mechanics terms, we translate thermodynamics results to learning scenarios.…

Statistical Mechanics · Physics 2025-01-07 Akshay Balsubramani

Successful human-robot teaming will require robots to adapt autonomously to a human teammate's internal state, where a critical element of such adaptation is the ability to estimate the human's workload in unknown situations. Existing…

Robotics · Computer Science 2025-07-11 Josh Bhagat Smith , Julie A. Adams