activity
20232025
most citedExtreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics

3 citations · 9 across the 8 of their papers we have counts for

collaborators

8 papers

cond-mat.soft2025

Capturing the fractocohesive length scale through a gradient-enhanced damage model for elastomers

S. Mohammad Mousavi, Jason Mulderrig, Brandon Talamini +1

This study aims to unravel the micro-mechanical underpinnings of the emergence of the fractocohesive length scale as a central concept in modern fracture mechanics. A thermodynamic…

cs.LG20241 cited

Condensed Stein Variational Gradient Descent for Uncertainty Quantification of Neural Networks

Govinda Anantha Padmanabha, Cosmin Safta, Nikolaos Bouklas +1

We propose a Stein variational gradient descent method to concurrently sparsify, train, and provide uncertainty quantification of a complexly parameterized model such as a neural n…

cond-mat.mtrl-sci2024

Evaluating fracture energy predictions using phase-field and gradient-enhanced damage models for elastomers

S. Mohammad Mousavi, Ida Ang, Jason Mulderrig +1

Recently, the phase field method has been increasingly used for brittle fractures in soft materials like polymers, elastomers, and biological tissues. When considering finite defor…

cs.LG20242 cited

Improving the performance of Stein variational inference through extreme sparsification of physically-constrained neural network models

Govinda Anantha Padmanabha, Jan Niklas Fuhg, Cosmin Safta +2

Most scientific machine learning (SciML) applications of neural networks involve hundreds to thousands of parameters, and hence, uncertainty quantification for such models is plagu…

cs.CE20233 cited

Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics

Jan N. Fuhg, Reese E. Jones, Nikolaos Bouklas

Data-driven constitutive modeling with neural networks has received increased interest in recent years due to its ability to easily incorporate physical and mechanistic constraints…

cond-mat.soft20231 cited

Stress representations for tensor basis neural networks: alternative formulations to Finger-Rivlin-Ericksen

Jan N. Fuhg, Nikolaos Bouklas, Reese E. Jones

Data-driven constitutive modeling frameworks based on neural networks and classical representation theorems have recently gained considerable attention due to their ability to easi…