Hebbian Physics Networks: A Self-Organizing Computational Architecture Based on Local Physical Laws

• URL: http://arxiv.org/abs/2507.00641v1
• Date: Tue, 01 Jul 2025 10:34:14 GMT
• Title: Hebbian Physics Networks: A Self-Organizing Computational Architecture Based on Local Physical Laws
• Abstract summary: Hebbian Physics Network (HPN) is a self-organizing computational framework in which learning emerges from local Hebbian updates driven by violations of conservation laws.<n>We demonstrate this approach on computation incompressible fluid flow and continuum diffusion, where physically consistent structures emerge from random initial conditions without supervision.
• Score: 1.0533738606966752
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traditional machine learning approaches in physics rely on global optimization, limiting interpretability and enforcing physical constraints externally. We introduce the Hebbian Physics Network (HPN), a self-organizing computational framework in which learning emerges from local Hebbian updates driven by violations of conservation laws. Grounded in non-equilibrium thermodynamics and inspired by Prigogine/'s theory of dissipative structures, HPNs eliminate the need for global loss functions by encoding physical laws directly into the system/'s local dynamics. Residuals - quantified imbalances in continuity, momentum, or energy - serve as thermodynamic signals that drive weight adaptation through generalized Hebbian plasticity. We demonstrate this approach on incompressible fluid flow and continuum diffusion, where physically consistent structures emerge from random initial conditions without supervision. HPNs reframe computation as a residual-driven thermodynamic process, offering an interpretable, scalable, and physically grounded alternative for modeling complex dynamical systems.

Related papers

• Physics-Informed Deep Learning for Entropy Prediction in Heterogeneous Systems: Thermodynamic and Information-Theoretic Case Studies [0.0]
  Entropy governs irreversibility and uncertainty in both physical and information-theoretic systems.<n>This paper introduces a unified Physics-Informed Deep Learning framework that simultaneously enforces differential equation residuals and information-theoretic bounds.
  arXiv  Detail & Related papers  (2026-05-31T11:38:52Z)
• A Comparative Investigation of Thermodynamic Structure-Informed Neural Networks [1.3965477771846408]
  Physics-informed neural networks (PINNs) offer a unified framework for solving both forward and inverse problems of differential equations.<n>We present a systematic comparison of different thermodynamic structure-informed neural networks by incorporating various thermodynamics formulations.
  arXiv  Detail & Related papers  (2026-03-26T07:39:15Z)
• EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp Generation [54.09734511705173]
  EFF-Grasp is a Flow-Matching synthesis-based framework for physics-aware dexterous grasp generation.<n>We reformulate grasp as a deterministic ordinary differential equation (ODE) process, which enables efficient and stable generation through smooth probability flows.<n> EFF-Grasp achieves superior performance in grasp quality and physical feasibility, while requiring substantially fewer sampling steps than diffusion-based baselines.
  arXiv  Detail & Related papers  (2026-03-17T06:11:56Z)
• OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning [51.33849811496781]
  Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous dynamics by Partial Differential Equations (PDEs)<n>We propose OMNIFLOW, a multimodal-symbolic architecture designed to ground frozen LLMs in fundamental physical laws without requiring domain-specific parameter updates.<n>We evaluate it on a benchmark spanning microscopic turbulence, theoretical Navier-Stokes, and macroscopic global weather forecasting.
  arXiv  Detail & Related papers  (2026-03-16T18:29:01Z)
• Conditional Denoising Model as a Physical Surrogate Model [1.0616273526777913]
  We introduce a generative model designed to learn the geometry of the physical manifold itself.<n>By training the network to restore clean states from noisy ones, the model learns a vector field that points continuously towards the valid solution subspace.
  arXiv  Detail & Related papers  (2026-01-28T20:32:20Z)
• PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models [100.65199317765608]
  Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation.<n>We introduce a physics-aware reinforcement learning paradigm for video generation models that enforces physical collision rules directly in high-dimensional spaces.<n>We extend this paradigm to a unified framework, termed Mimicry-Discovery Cycle (MDcycle), which allows substantial fine-tuning.
  arXiv  Detail & Related papers  (2026-01-16T08:40:10Z)
• Enforcing hidden physics in physics-informed neural networks [3.41772976335063]
  We introduce a simple, generalized, yet robust irreversibility-regularized strategy that enforces hidden physical laws as soft constraints during training.<n>We demonstrate that our regularization scheme reduces predictive errors by more than an order of magnitude, while requiring only minimal modification to existing PINN frameworks.
  arXiv  Detail & Related papers  (2025-11-18T10:52:37Z)
• Universal Physics Simulation: A Foundational Diffusion Approach [0.0]
  We present the first foundational AI model for universal physics simulation that learns physical laws directly from boundary-condition data.<n>Our sketch-guided diffusion transformer approach reimagines computational physics by treating simulation as a conditional generation problem.<n>Unlike sequential time-stepping methods that accumulate errors over iterations, our approach bypasses temporal integration entirely.
  arXiv  Detail & Related papers  (2025-07-13T18:12:34Z)
• KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches [43.872190335490515]
  This paper introduces KITINet, a novel architecture that reinterprets feature propagation through the lens of non-equilibrium particle dynamics.<n>At its core, we propose a residual module that models update as the evolution of a particle system.<n>This formulation mimics particle collisions and energy exchange, enabling adaptive feature refinement via physics-informed interactions.
  arXiv  Detail & Related papers  (2025-05-23T13:58:29Z)
• Spatiotemporal Field Generation Based on Hybrid Mamba-Transformer with Physics-informed Fine-tuning [46.67399627400437]
  This research confronts the challenge of substantial physical equation discrepancies in the generation of physical fields through trained models.<n>A physical field generation model, named HMT-PF, is developed based on the hybrid Mamba-Transformer architecture.
  arXiv  Detail & Related papers  (2025-05-16T14:40:56Z)
• A Physics-Informed Spatiotemporal Deep Learning Framework for Turbulent Systems [0.0]
  We present a physics-informed RBC surrogate model for convection.<n>Our approach combines a canonical dimensional neural networks, for spatial reduction, with an innovative recurrent architecture, inspired by large language models.<n>This model replicates key physical features while reducing computational cost, offering a scalable alternative to DNS for long-term simulations.
  arXiv  Detail & Related papers  (2025-05-16T06:47:00Z)
• Advancing Generalization in PINNs through Latent-Space Representations [71.86401914779019]
  Physics-informed neural networks (PINNs) have made significant strides in modeling dynamical systems governed by partial differential equations (PDEs)<n>We propose PIDO, a novel physics-informed neural PDE solver designed to generalize effectively across diverse PDE configurations.<n>We validate PIDO on a range of benchmarks, including 1D combined equations and 2D Navier-Stokes equations.
  arXiv  Detail & Related papers  (2024-11-28T13:16:20Z)
• Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling [41.82469276824927]
  We present a framework that achieves high-precision modeling for a wide range of dynamical systems. It helps preserve energies for conservative systems while serving as a strong inductive bias for non-conservative, reversible systems. By integrating the TRS loss within neural ordinary differential equation models, the proposed model TREAT demonstrates superior performance on diverse physical systems.
  arXiv  Detail & Related papers  (2024-10-08T21:04:01Z)
• A physics-encoded Fourier neural operator approach for surrogate modeling of divergence-free stress fields in solids [6.877349053520825]
  A so-called physics-encoded Fourier neural operator (PeFNO) is developed for surrogate modeling of the quasi-static equilibrium stress field in solids.<n>Stress field data for training are obtained from the numerical solution of a corresponding boundary-value problem for quasi-static mechanical equilibrium.<n>The output of the trained PeFNO is significantly more accurate in satisfying mechanical equilibrium than the output of either the trained PgFNO or the trained PiFNO.
  arXiv  Detail & Related papers  (2024-08-27T21:18:41Z)
• Thermodynamics-Consistent Graph Neural Networks [50.0791489606211]
  We propose excess Gibbs free energy graph neural networks (GE-GNNs) for predicting composition-dependent activity coefficients of binary mixtures. The GE-GNN architecture ensures thermodynamic consistency by predicting the molar excess Gibbs free energy. We demonstrate high accuracy and thermodynamic consistency of the activity coefficient predictions.
  arXiv  Detail & Related papers  (2024-07-08T06:58:56Z)
• TANGO: Time-Reversal Latent GraphODE for Multi-Agent Dynamical Systems [43.39754726042369]
  We propose a simple-yet-effective self-supervised regularization term as a soft constraint that aligns the forward and backward trajectories predicted by a continuous graph neural network-based ordinary differential equation (GraphODE) It effectively imposes time-reversal symmetry to enable more accurate model predictions across a wider range of dynamical systems under classical mechanics. Experimental results on a variety of physical systems demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2023-10-10T08:52:16Z)
• Machine learning in and out of equilibrium [58.88325379746631]
  Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels. We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium. We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
  arXiv  Detail & Related papers  (2023-06-06T09:12:49Z)
• Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics [97.38308257547186]
  Many NN approaches learn an end-to-end model that implicitly models both the governing PDE and material models. We argue that the governing PDEs are often well-known and should be explicitly enforced rather than learned. We introduce a new framework termed "Neural Constitutive Laws" (NCLaw) which utilizes a network architecture that strictly guarantees standard priors.
  arXiv  Detail & Related papers  (2023-04-27T17:42:24Z)
• No-Signaling in Steepest Entropy Ascent: A Nonlinear Non-local Non-equilibrium Quantum Dynamics of Composite Systems [0.0]
  Lindbladian formalism models open quantum systems using a 'bottom-up' approach, deriving linear dynamics from system-environment interactions.<n>We present a 'top-down' approach, focusing on system's structure, subsystems' interactions, environmental effects.<n>We show that incorporating the second law's requirement -- that Gibbs states are the sole stable equilibria -- necessitates nonlinear dynamics.
  arXiv  Detail & Related papers  (2023-01-27T06:22:27Z)
• NN-EUCLID: deep-learning hyperelasticity without stress data [0.0]
  We propose a new approach for unsupervised learning of hyperelastic laws with physics-consistent deep neural networks. In contrast to supervised learning, which assumes the stress-strain, the approach only uses realistically measurable full-elastic field displacement and global force availability data.
  arXiv  Detail & Related papers  (2022-05-04T13:54:54Z)
• Physics informed neural networks for continuum micromechanics [68.8204255655161]
  Recently, physics informed neural networks have successfully been applied to a broad variety of problems in applied mathematics and engineering. Due to the global approximation, physics informed neural networks have difficulties in displaying localized effects and strong non-linear solutions by optimization. It is shown, that the domain decomposition approach is able to accurately resolve nonlinear stress, displacement and energy fields in heterogeneous microstructures obtained from real-world $mu$CT-scans.
  arXiv  Detail & Related papers  (2021-10-14T14:05:19Z)
• Encoding physics to learn reaction-diffusion processes [18.187800601192787]
  We show how a deep learning framework that encodes given physics structure can be applied to a variety of problems regarding the PDE system regimes. The resultant learning paradigm that encodes physics shows high accuracy, robustness, interpretability and generalizability demonstrated via extensive numerical experiments.
  arXiv  Detail & Related papers  (2021-06-09T03:02:20Z)
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling [86.9726984929758]
  We focus on the integration of incomplete physics models into deep generative models. We propose a VAE architecture in which a part of the latent space is grounded by physics. We demonstrate generative performance improvements over a set of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-25T20:28:52Z)
• Structure-preserving neural networks [0.08209843760716957]
  We develop a method to learn physical systems from data that employs feedforward neural networks. The method employs a minimum amount of data by enforcing the metriplectic structure of dissipative Hamiltonian systems.
  arXiv  Detail & Related papers  (2020-04-09T16:41:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.