English
Related papers

Related papers: Thermodynamic Neural Network

200 papers

Networks are ubiquitous throughout science and engineering. A number of methods, including some from our own group, have explored how one goes about computing or predicting the dynamics of networks given information about internal models of…

Molecular Networks · Quantitative Biology 2017-11-06 Gabriel A. Silva

The spring network model constitutes the backbone in the representations of a host of physical systems. In this work, we report the disturbance-driven microscopic dynamics of an isolated, closed spring network of spherical topology in…

Soft Condensed Matter · Physics 2025-08-26 Zhenwei Yao

The objective of this paper is to design novel multi-layer neural network architectures for multiscale simulations of flows taking into account the observed data and physical modeling concepts. Our approaches use deep learning concepts…

Numerical Analysis · Mathematics 2018-06-14 Yating Wang , Siu Wun Cheung , Eric T. Chung , Yalchin Efendiev , Min Wang

We analyze transport on a graph with multiple constraints and where the weight of the edges connecting the nodes is a dynamical variable. The network dynamics results from the interplay between a nonlinear function of the flow, dissipation,…

Statistical Mechanics · Physics 2023-11-28 Frederic Folz , Kurt Mehlhorn , Giovanna Morigi

In this review, we describe the singular success of attractor neural network models in describing how the brain maintains persistent activity states for working memory, error-corrects, and integrates noisy cues. We consider the mechanisms…

Neurons and Cognition · Quantitative Biology 2022-03-03 Mikail Khona , Ila R. Fiete

In recent years, augmentation of differentiable PDE solvers with neural networks has shown promising results, particularly in fluid simulations. However, most approaches rely on convolutional neural networks and custom solvers operating on…

Machine Learning · Computer Science 2025-02-27 Matthias Schulz , Gwendal Jouan , Daniel Berger , Stefan Gavranovic , Dirk Hartmann

We study network properties of networks evolving in time based on optimal transport principles. These evolve from a structure covering uniformly a continuous space towards an optimal design in terms of optimal transport theory. At…

Physics and Society · Physics 2023-10-25 Diego Baptista , Caterina De Bacco

We propose a hierarchically modular, dynamical neural network model whose architecture minimizes a specifically designed energy function and defines its temporal characteristics. The model has an internal and an external space that are…

Neurons and Cognition · Quantitative Biology 2026-04-16 Kazuyoshi Tsutsumi , Ernst Niebur

The study of intelligent systems explains behaviour in terms of economic rationality. This results in an optimization principle involving a function or utility, which states that the system will evolve until the configuration of maximum…

Information Theory · Computer Science 2024-06-18 Pedro Hack

Understanding the training dynamics of deep neural networks remains a major open problem, with physics-inspired approaches offering promising insights. Building on this perspective, we develop a thermodynamic framework to describe the…

Machine Learning · Computer Science 2026-05-15 Ildus Sadrtdinov , Ekaterina Lobacheva , Ivan Klimov , Mikhail Burtsev , Mikhail I. Katsnelson , Dmitry Vetrov

Empirical complex systems must differentially respond to external perturbations and, at the same time, internally distribute information to coordinate their components. While networked backbones help with the latter, they limit the…

Physics and Society · Physics 2025-04-18 Arsham Ghavasieh , Manlio De Domenico

Recent advances at the intersection of control theory, neuroscience, and machine learning have revealed novel mechanisms by which dynamical systems perform computation. These advances encompass a wide range of conceptual, mathematical, and…

Machine Learning · Computer Science 2026-04-10 Arthur N. Montanari , Francesco Bullo , Dmitry Krotov , Adilson E. Motter

The use of artificial neural networks as models of chaotic dynamics has been rapidly expanding. Still, a theoretical understanding of how neural networks learn chaos is lacking. Here, we employ a geometric perspective to show that neural…

Machine Learning · Computer Science 2021-07-02 Ziwei Li , Sai Ravela

Given observations of a physical system, identifying the underlying non-linear governing equation is a fundamental task, necessary both for gaining understanding and generating deterministic future predictions. Of most practical relevance…

Numerical Analysis · Mathematics 2020-03-02 A. Goeßmann , M. Götte , I. Roth , R. Sweke , G. Kutyniok , J. Eisert

In this paper we present a deep learning method to predict the temporal evolution of dissipative dynamic systems. We propose using both geometric and thermodynamic inductive biases to improve accuracy and generalization of the resulting…

Machine Learning · Computer Science 2022-06-07 Quercus Hernández , Alberto Badías , Francisco Chinesta , Elías Cueto

In this paper, we provide sufficient conditions for dissipativity and local asymptotic stability of discrete-time dynamical systems parametrized by deep neural networks. We leverage the representation of neural networks as pointwise affine…

Machine Learning · Computer Science 2022-06-09 Jan Drgona , Soumya Vasisht , Aaron Tuor , Draguna Vrabie

In this and a companion paper we outline a general framework for the thermodynamic description of open chemical reaction networks, with special regard to metabolic networks regulating cellular physiology and biochemical functions. We first…

Chemical Physics · Physics 2014-10-22 Matteo Polettini , Massimiliano Esposito

The promise of chemical computation lies in controlling systems incompatible with traditional electronic micro-controllers, with applications in synthetic biology and nano-scale manufacturing. Computation is typically embedded in…

Emerging Technologies · Computer Science 2019-02-11 Keenan Breik , Chris Thachuk , Marijn Heule , David Soloveichik

The last decade has shown a tremendous success in solving various computer vision problems with the help of deep learning techniques. Lately, many works have demonstrated that learning-based approaches with suitable network architectures…

Machine Learning · Computer Science 2019-08-21 Michael Moeller , Thomas Möllenhoff , Daniel Cremers

Deep learning models are yielding increasingly better performances thanks to multiple factors. To be successful, model may have large number of parameters or complex architectures and be trained on large dataset. This leads to large…

Machine Learning · Computer Science 2022-12-20 Jean-Roch Vlimant , Junqi Yin