English
Related papers

Related papers: Physical networks become what they learn

200 papers

Deep neural networks (DNNs) have achieved exceptional performance across various fields by learning complex, nonlinear mappings from large-scale datasets. However, they face challenges such as high memory requirements and computational…

Machine Learning · Computer Science 2025-04-21 Callen MacPhee , Yiming Zhou , Bahram Jalali

Network routing approaches are widely used to study the evolution in time of self-adapting systems. However, few advances have been made for problems where adaptation is governed by time-dependent inputs. In this work we study a dynamical…

Physics and Society · Physics 2023-10-25 Alessandro Lonardi , Enrico Facca , Mario Putti , Caterina De Bacco

We study a material modeled as a network of nodes connected by edges. Using a discrete approach, we build a nonlinear algebraic system that connects applied forces to internal forces and node positions. The model can describe elasticity,…

Optimization and Control · Mathematics 2025-10-14 Ioannis Dassios

Efficient networking has a substantial economic and societal impact in a broad range of areas including transportation systems, wired and wireless communications and a range of Internet applications. As transportation and communication…

Physics and Society · Physics 2015-05-30 Chi Ho Yeung , David Saad

Physics-informed neural networks approach the approximation of differential equations by directly incorporating their structure and given conditions in a loss function. This enables conditions like, e.g., invariants to be easily added…

Machine Learning · Computer Science 2025-08-20 Santosh Humagain , Toni Schneidereit

Given an existing trained neural network, it is often desirable to learn new capabilities without hindering performance of those already learned. Existing approaches either learn sub-optimal solutions, require joint training, or incur a…

Computer Vision and Pattern Recognition · Computer Science 2018-02-15 Amir Rosenfeld , John K. Tsotsos

The computational modeling of high-speed flows (e.g. hypersonic) and space plasmas is characterized by a plethora of complex physical phenomena, in particular involving strong oblique shocks, bow shocks and/or shock waves boundary layer…

Computational Physics · Physics 2025-11-19 Firas Ben Ameur , Andrea Lani

We study adaptive network models in which coupling weights evolve on a fast time scale relative to the phase dynamics of the nodes. Using Geometric Singular Perturbation Theory (GSPT), we prove that, although the microscopic system is…

Dynamical Systems · Mathematics 2026-03-23 Christian Kuehn , Fergal Murphy

We present E NERGY N ET , a new framework for analyzing and building artificial neural network architectures. Our approach adaptively learns the structure of the networks in an unsupervised manner. The methodology is based upon the…

Machine Learning · Computer Science 2017-11-10 Gus Kristiansen , Xavi Gonzalvo

To make sense of the world our brains must analyze high-dimensional datasets streamed by our sensory organs. Because such analysis begins with dimensionality reduction, modelling early sensory processing requires biologically plausible…

Neurons and Cognition · Quantitative Biology 2016-01-27 Cengiz Pehlevan , Dmitri B. Chklovskii

Deep neural networks (DNN) have been used to model nonlinear relations between physical quantities. Those DNNs are embedded in physical systems described by partial differential equations (PDE) and trained by minimizing a loss function that…

Numerical Analysis · Mathematics 2020-02-26 Kailai Xu , Eric Darve

We study the effect of mini-batching on the loss landscape of deep neural networks using spiked, field-dependent random matrix theory. We demonstrate that the magnitude of the extremal values of the batch Hessian are larger than those of…

Machine Learning · Statistics 2021-11-08 Diego Granziol , Stefan Zohren , Stephen Roberts

Adaptive networks are a versatile approach to model phenomena such as contagion and spreading dynamics, critical transitions and structure formation that emerge from the dynamic coevolution of complex network structure and node states.…

Physics and Society · Physics 2020-09-16 Fabian Geier , Wolfram Barfuss , Marc Wiedermann , Jürgen Kurths , Jonathan F. Donges

Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics. How might we endow them with better inductive biases? In this paper, we draw inspiration from Hamiltonian mechanics to train models…

Neural and Evolutionary Computing · Computer Science 2019-09-06 Sam Greydanus , Misko Dzamba , Jason Yosinski

Deep learning approaches, known for their ability to model complex relationships and fast execution, are increasingly being applied to solve large optimization problems. However, existing methods often face challenges in simultaneously…

Optimization and Control · Mathematics 2025-12-16 Zisheng Zhou , Dengyu Zheng , Zirui Chen , Shixiang Chen

All living things exhibit adaptations that enable them to survive and reproduce in the natural environment that they inhabit. From a biological standpoint, it has long been understood that adaptation comes from natural selection, whereby…

Biological Physics · Physics 2016-06-22 Nikolai Perunov , Robert Marsland , Jeremy England

The Hessian of a neural network captures parameter interactions through second-order derivatives of the loss. It is a fundamental object of study, closely tied to various problems in deep learning, including model design, optimization, and…

Machine Learning · Computer Science 2021-07-02 Sidak Pal Singh , Gregor Bachmann , Thomas Hofmann

Mathematical modeling has broad applications in neuroscience whether modeling the dynamics of a single synapse or an entire network of neurons. In Part I, we model vesicle replenishment and release at the photoreceptor synapse to better…

Neurons and Cognition · Quantitative Biology 2017-02-23 Caitlyn M. Parmelee

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

Machine Learning · Computer Science 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

In this paper, we propose an optimization framework to design a network of positive linear systems whose structure switches according to a Markov process. The optimization framework herein proposed allows the network designer to optimize…

Optimization and Control · Mathematics 2019-03-19 Masaki Ogura , Victor M. Preciado
‹ Prev 1 8 9 10 Next ›