English
Related papers

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

200 papers

Structured meshes, composed of quadrilateral elements in 2D and hexahedral elements in 3D, are widely used in industrial applications and engineering simulations due to their regularity and superior accuracy in finite element analysis.…

Graphics · Computer Science 2026-03-16 Xiaoyang Yu , Canjia Huang , Zhonggui Chen , Juan Cao

This paper introduces a new probabilistic framework for supervised learning in neural systems. It is designed to model complex, uncertain systems whose random outputs are strongly non-Gaussian given deterministic inputs. The architecture…

Machine Learning · Statistics 2025-12-12 Christian Soize

In this article, we present an extension of the Tensorflow Playground, called Tensorflow Meter (short TFMeter). TFMeter is an interactive neural network architecting tool that allows the visual creation of different architectures of neural…

Machine Learning · Computer Science 2021-01-14 Henrik Hoeiness , Axel Harstad , Gerald Friedland

We propose a metriplectic reformulation of Lagrangian variational formulations for non-equilibrium thermodynamics. We prove that solutions to these constrained variational principles can be generated by the sum of a classic Poisson bracket…

Mathematical Physics · Physics 2025-05-23 Valentin Carlier

Theory-guided machine learning has demonstrated that including authentic domain knowledge directly into model design improves performance, sample efficiency and out-of-distribution generalisation. Yet the process by which a formal domain…

Machine Learning · Computer Science 2026-03-17 Asela Hevapathige , Yu Xia , Sachith Seneviratne , Saman Halgamuge

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task related neural dynamics we study trained Recurrent Neural Networks. We develop a Mean Field Theory for Reservoir Computing…

Neurons and Cognition · Quantitative Biology 2017-06-28 Alexander Rivkind , Omri Barak

Mean-field theory is a powerful tool for studying large neural networks. However, when the system is composed of a few neurons, macroscopic differences between the mean-field approximation and the real behavior of the network can arise.…

Neurons and Cognition · Quantitative Biology 2016-09-28 Diego Fasoli , Anna Cattani , Stefano Panzeri

Tensor is the most basic and essential data structure of nowadays artificial intelligence (AI) system. The natural properties of Tensor, especially the memory-continuity and slice-independence, make it feasible for training system to…

Artificial Intelligence · Computer Science 2026-02-13 Shaoang Zhang , Yazhe Niu

We define regularised Poisson brackets for the monodromy matrix of classical string theory on R x S^3. The ambiguities associated with Non-Ultra Locality are resolved using the symmetrisation prescription of Maillet. The resulting brackets…

High Energy Physics - Theory · Physics 2010-10-27 Nick Dorey , Benoit Vicedo

Machine learning tasks are generally formulated as optimization problems, where one searches for an optimal function within a certain functional space. In practice, parameterized functional spaces are considered, in order to be able to…

Artificial Intelligence · Computer Science 2024-12-13 Manon Verbockhaven , Sylvain Chevallier , Guillaume Charpiat , Théo Rudkiewicz

Neural state-of-the-art sequence-to-sequence (seq2seq) models often do not perform well for small training sets. We address paradigm completion, the morphological task of, given a partial paradigm, generating all missing forms. We propose…

Computation and Language · Computer Science 2019-05-10 Katharina Kann , Hinrich Schütze

Recent development in computer processing power leads to new paradigms of how problems in many-body physics and especially polymer physics can be addressed. GPU parallel processors can be employed to generate millions of independent…

Soft Condensed Matter · Physics 2019-05-01 Marco Werner , Yachong Guo , Vladimir A. Baulin

A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible. Current architectures, however, cannot be applied beyond a small set of stereotyped settings, as they bake in…

Tsetlin Machine (TM) has been gaining popularity as an inherently interpretable machine leaning method that is able to achieve promising performance with low computational complexity on a variety of applications. The interpretability and…

Machine Learning · Computer Science 2022-12-29 Jivitesh Sharma , Ole-Christoffer Granmo , Lei Jiao

Flows on symplectic, Poisson, contact, and metriplectic manifolds are reviewed in order to describe our main result, which is to associate a natural metriplectic dynamical system on the general one-jet bundle $J^1N=T^*N\times \mathbb{R}$,…

Symplectic Geometry · Mathematics 2026-05-12 Philip J. Morrison , Yong-Geun Oh

We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of energy,…

Machine Learning · Computer Science 2023-03-28 Quercus Hernández , Alberto Badías , Francisco Chinesta , Elías Cueto

One of the main challenges of Topological Data Analysis (TDA) is to extract features from persistent diagrams directly usable by machine learning algorithms. Indeed, persistence diagrams are intrinsically (multi-)sets of points in…

Machine Learning · Computer Science 2022-09-27 Raphael Reinauer , Matteo Caorsi , Nicolas Berkouk

Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file…

Artificial Intelligence · Computer Science 2026-05-26 Bronislav Sidik , Lior Rokach

Recent advances in the theory of Neural Operators (NOs) have enabled fast and accurate computation of the solutions to complex systems described by partial differential equations (PDEs). Despite their great success, current NO-based…

Machine Learning · Computer Science 2024-03-18 Ashutosh Singh , Ricardo Augusto Borsoi , Deniz Erdogmus , Tales Imbiriba

This paper presents a unified mixed-integer programming framework for training sparse and interpretable neural networks. We develop exact formulations for both fully connected and convolutional architectures by modeling nonlinearities such…

Artificial Intelligence · Computer Science 2025-04-22 Masoud Ataei , Edrin Hasaj , Jacob Gipp , Sepideh Forouzi