Exploring the potential of transfer learning for metamodels of heterogeneous material deformation
Explore this paper's citation graph
Summary
This paper extends Mechanical MNIST, an open source benchmark dataset of heterogeneous material undergoing large deformation, to include a selection of low-fidelity simulation results that require ≈ 2 - 4 orders of magnitude less CPU time to run, and shows that transfer learning can vastly improve the performance of metamodels used to predict the results of high-f fidelity simulations.
- Type
- preprint
- Published
- 2020-10-28
- Cited by
- 20
- References
- 63
- Access
- Open access
- OpenAlex
- https://openalex.org/W3097894508
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:226222304
Keywords
Computer science, Leverage (statistics), Fidelity, Transfer of learning, MNIST database
References
- Automated Solution of Differential Equations by the Finite Element Method: The FEniCS Book
- Computational aspects of growth-induced instabilities through eigenvalue analysis
- Constrained optimization of an idealized Y-shaped baffle for the Fontan surgery at rest and exercise
- Surrogate-based Analysis and Optimization
- Perspectives on biological growth and remodeling
- Solution of the nonlinear elasticity imaging inverse problem: the compressible case
- Detection of seals in remote sensing images using features extracted from deep convolutional neural networks
- Heterogeneous growth-induced prestrain in the heart
- Gradient-based learning applied to document recognition
- A Survey on Transfer Learning
- The FEniCS Project Version 1.5
- Transfer of Learning
- Food image recognition using deep convolutional network with pre-training and fine-tuning
- Self-consistent clustering analysis: An efficient multi-scale scheme for inelastic heterogeneous materials
- Surrogate-based methods for black-box optimization
- Tri-layer wrinkling as a mechanism for anchoring center initiation in the developing cerebellum.
- A Computational Model of the Biochemomechanics of an Evolving Occlusive Thrombus
- A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality
- Printing nature: Unraveling the role of nacre's mineral bridges.
- Searching for Activation Functions
Cited by
- Data-driven Modeling of the Mechanical Behavior of Anisotropic Soft Biological Tissue
- Predicting Mechanically Driven Full-Field Quantities of Interest with Deep Learning-Based Metamodels
- Predicting the mechanical properties of biopolymer gels using neural networks trained on discrete fiber network data
- Diagnosis of Bronchial and Pulmonary Fungal Infection Using Gradient Weighted Denoising Algorithm-Based CT Images
- Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps
- Machine Learning for Cardiovascular Biomechanics Modeling: Challenges and Beyond
- Reduced-order modeling of conductive polymer pressure sensors using finite element simulations and deep neural networks
- Learning Mechanically Driven Emergent Behavior with Message Passing Neural Networks
- Enhancing Mechanical Metamodels with a Generative Model-Based Augmented Training Dataset
- Towards out of distribution generalization for problems in mechanics
- Mechanical properties prediction of various graphene reinforced nanocomposites using transfer learning-based deep neural network
- Can machine learning accelerate soft material parameter identification from complex mechanical test data?
- Intuitionistic fuzzy three-way transfer learning based on rough almost stochastic dominance
- SenseNet: A Physics-Informed Deep Learning Model for Shape Sensing
- WarpPINN: Cine-MR image registration with physics-informed neural networks
- Short-term traffic flow prediction of parallel roads based on transfer learning
- Cooperative data-driven modeling
- Integrating uncertainty into deep learning models for enhanced prediction of nanocomposite materials’ mechanical properties
- MatSwarm: trusted swarm transfer learning driven materials computation for secure big data sharing
- Multifidelity Kolmogorov–Arnold networks
Related papers
- Falsification of Learning-Based Controllers through Multi-Fidelity Bayesian Optimization
- Initial sampling using multi-fidelity information in simulation optimization of manufacturing systems
- Falsification of Learning-Based Controllers through Multi-Fidelity Bayesian Optimization
- Fidelity concepts used in UWB systems
- Vector Fidelity Analyses of Seabed Seismic Data
- Utilizing an Adjustment Factor to Scale Between Multiple Fidelities Within a Design Process: A Stepping Stone to Dialable Fidelity Design
- High Fidelity, High Performance?
- A Machine Learning Framework for Physics-Based Multi-Fidelity Modeling and Health Monitoring for a Composite Wing