Differentiable neural network representation of multi-well, locally-convex potentials

DOI10.1016/J.JCP.2026.114688MaRDI QIDQ7235783zbMATH OpenFDO

Authors Reese Edward Jones, Adrián Buganza Tepole, Jan N. Fuhg

Publication date 29 April 2026

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCP.2026.114688

zbMATH Keywords

bifurcationlocal convexitylog-sum-exponentialmulti-well potentialsneural networksphase change

Mathematics Subject Classification ID

Generalities, axiomatics, foundations of continuum mechanics of solids (74Axx) Numerical and other methods in solid mechanics (74Sxx) Mathematical programming (90Cxx)

Cites work

• A mechanics‐informed artificial neural network approach in data‐driven constitutive modeling
• Accurately computing the log-sum-exp and softmax functions
• An assessment of numerical techniques to find energy-minimizing microstructures associated with nonconvex potentials
• Automated model discovery of finite strain elastoplasticity from uniaxial experiments
• Convexity conditions and existence theorems in nonlinear elasticity
• Data-driven tissue mechanics with polyconvex neural ordinary differential equations
• Double wells
• scientific article; zbMATH DE number 3483647 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• Learning constitutive relations using symmetric positive definite neural networks
• Loss of polyconvexity by homogenization
• Multi-well potentials in quantum mechanics and stochastic processes
• Neural network-based multiscale modeling of finite strain magneto-elasticity with relaxed convexity criteria
• Nonlocal phase transitions in homogeneous and periodic media
• On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling
• On the relation of a three-well energy
• Pattern recognition and machine learning.
• Smooth minimization of non-smooth functions
• Smoothing and first order methods: a unified framework
• Smoothing method for minimax problems
• Sparse regression: scalable algorithms and empirical performance
• Spectral representation and reduced order modeling of the dynamics of stochastic reaction networks via adaptive data partitioning
• The Derivation of Constitutive Relations from the Free Energy and the Dissipation Function
• The double-well potential in quantum mechanics: a simple, numerically exact formulation
• The relaxation of a double-well energy
• Using the \(L\)-curve for determining optimal regularization parameters

This page was built for publication: Differentiable neural network representation of multi-well, locally-convex potentials

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7235783)