English
Related papers

Related papers: Metriplector: From Field Theory to Neural Architec…

200 papers

A dynamical system defined by a metriplectic structure is a dissipative model characterized by a specific pair of tensors, which defines the Leibniz brackets. Generally, these tensors are Poisson brackets tensor and a symmetric metric…

General Physics · Physics 2018-04-03 Giulia Marcucci , Claudio Conti , Massimo Materassi

The metriplectic formalism couples Poisson brackets of the Hamiltonian description with metric brackets for describing systems with both Hamiltonian and dissipative components. The construction builds in asymptotic convergence to a…

Classical Physics · Physics 2017-06-07 Massimo Materassi , Philip J. Morrison

Metriplectic dynamics couple a Poisson bracket of the Hamiltonian description with a kind of metric bracket, for describing systems with both Hamiltonian and dissipative components. The construction builds in asymptotic convergence to a…

Classical Physics · Physics 2018-07-04 Massimo Materassi , Philip J. Morrison

Context. Metamorphic Testing is recognised in IEEE/ISO software-testing standards and increasingly recommended for AI systems, but its progress is bottlenecked by metamorphic relation (MR) identification: existing approaches (structured…

Software Engineering · Computer Science 2026-05-19 Meng Li , Xiaohua Yang , Jie Liu , Shiyu Yan

We develop a method to learn physical systems from data that employs feedforward neural networks and whose predictions comply with the first and second principles of thermodynamics. The method employs a minimum amount of data by enforcing…

Machine Learning · Computer Science 2020-11-16 Quercus Hernández , Alberto Badias , David Gonzalez , Francisco Chinesta , Elias Cueto

Metriplectic systems are learned from data in a way that scales quadratically in both the size of the state and the rank of the metriplectic data. Besides being provably energy conserving and entropy stable, the proposed approach comes with…

Machine Learning · Computer Science 2025-01-28 Anthony Gruber , Kookjin Lee , Haksoo Lim , Noseong Park , Nathaniel Trask

We propose Nester, a method for injecting neural networks into constrained structured predictors. The job of the neural network(s) is to compute an initial, raw prediction that is compatible with the input data but does not necessarily…

Machine Learning · Computer Science 2021-04-01 Paolo Dragone , Stefano Teso , Andrea Passerini

Scientific machine learning often requires combining known physics with unknown parameters or correction terms learned from data. Existing approaches either ignore known structure, encode it as a soft penalty, or require hand-written…

Machine Learning · Computer Science 2026-05-22 Lucas Sheneman

A novel Neural Network architecture is proposed using the mathematically and physically rich idea of vector fields as hidden layers to perform nonlinear transformations in the data. The data points are interpreted as particles moving along…

Machine Learning · Computer Science 2018-02-23 Daniel Vieira , Fabio Rangel , Fabricio Firmino , Joao Paixao

Thermodynamics-informed neural networks employ inductive biases for the enforcement of the first and second principles of thermodynamics. To construct these biases, a metriplectic evolution of the system is assumed. This provides excellent…

Machine Learning · Computer Science 2025-01-22 Alicia Tierz , Iciar Alfaro , David González , Francisco Chinesta , Elías Cueto

We associate learning and adaptation in living systems with the shaping of the velocity vector field in the respective dynamical systems in response to external, generally random, stimuli. With this, a mathematical concept of self-shaping…

Adaptation and Self-Organizing Systems · Physics 2015-10-08 Natalia B. Janson , Christopher J. Marsden

Mean-field models of the mammalian cortex treat this part of the brain as a two-dimensional excitable medium. The electrical potentials, generated by the excitatory and inhibitory neuron populations, are described by nonlinear, coupled,…

Dynamical Systems · Mathematics 2018-11-19 Kevin R. Green , Lennaert van Veen

Neural networks transform high-dimensional data into compact, structured representations, often modeled as elements of a lower dimensional latent space. In this paper, we present an alternative interpretation of neural models as dynamical…

Machine Learning · Computer Science 2026-03-26 Marco Fumero , Luca Moschella , Emanuele Rodolà , Francesco Locatello

Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a…

Machine Learning · Computer Science 2017-02-16 Barret Zoph , Quoc V. Le

We study a model of interacting neurons. The structure of this neural system is composed of two layers of neurons such that the neurons of the first layer send their spikes to the neurons of the second one: if $N$ is the number of neurons…

Probability · Mathematics 2023-06-22 Xavier Erny

This work begins by establishing a mathematical formalization between different geometrical interpretations of Neural Networks, providing a first contribution. From this starting point, a new interpretation is explored, using the idea of…

Machine Learning · Computer Science 2019-05-20 Daniel Vieira , Joao Paixao

An inclusive framework for joined Hamiltonian and dissipative dynamical systems, which preserve energy and produce entropy, is given. The dissipative dynamics of the framework is based on the metriplectic 4-bracket, a quantity like the…

Mathematical Physics · Physics 2023-10-24 Philip J. Morrison , Michael H. Updike

In this paper, we present neural networks learning mechanical systems that are both symplectic (for instance particle mechanics) and non-symplectic (for instance rotating rigid body). Mechanical systems have Hamiltonian evolution, which…

Mathematical Physics · Physics 2023-05-10 Martin Šípka , Michal Pavelka , Oğul Esen , Miroslav Grmela

Metriplectic dynamical systems consist of a special combination of a Hamiltonian and a (generalized) entropy-gradient flow, such that the Hamiltonian is conserved and entropy is dissipated/produced (depending on a sign convention). It is…

Mathematical Physics · Physics 2026-04-06 C. Bressan , M. Kraus , O. Maj , P. J. Morrison

As it stands, a robust mathematical framework to analyse and study various topics in deep learning is yet to come to the fore. Nonetheless, viewing deep learning as a dynamical system allows the use of established theories to investigate…

Machine Learning · Computer Science 2022-07-26 Nader Ganaba
‹ Prev 1 2 3 10 Next ›