The following pages link to PyTorch (Q32752):
Displaying 50 items.
- Solving parametric partial differential equations with deep rectified quadratic unit neural networks (Q2103467) (← links)
- \(\pi\) VAE: a stochastic process prior for Bayesian deep learning with MCMC (Q2103969) (← links)
- Bayesian learning via neural Schrödinger-Föllmer flows (Q2104005) (← links)
- On the convergence analysis of aggregated heavy-ball method (Q2104283) (← links)
- Guiding an automated theorem prover with neural rewriting (Q2104548) (← links)
- Collective proposal distributions for nonlinear MCMC samplers: mean-field theory and fast implementation (Q2106803) (← links)
- Semi-implicit methods for advection equations with explicit forms of numerical solution (Q2107455) (← links)
- Non-homogeneous Poisson process intensity modeling and estimation using measure transport (Q2108510) (← links)
- Towards high-accuracy deep learning inference of compressible flows over aerofoils (Q2108599) (← links)
- Self-adaptive physics-informed neural networks (Q2112437) (← links)
- Learning stochastic dynamics with statistics-informed neural network (Q2112526) (← links)
- Nonlinear input feature reduction for data-based physical modeling (Q2112546) (← links)
- Stabilized neural ordinary differential equations for long-time forecasting of dynamical systems (Q2112549) (← links)
- Discriminative clustering with representation learning with any ratio of labeled to unlabeled data (Q2114048) (← links)
- Tool path optimization of selective laser sintering processes using deep learning (Q2115582) (← links)
- Between steps: intermediate relaxations between big-M and convex hull formulations (Q2117230) (← links)
- Iterative SE(3)-transformers (Q2117906) (← links)
- Metamorphic image registration using a semi-Lagrangian scheme (Q2117947) (← links)
- OptiLog: a framework for SAT-based systems (Q2118280) (← links)
- Use of static surrogates in hyperparameter optimization (Q2120124) (← links)
- GINNs: graph-informed neural networks for multiscale physics (Q2120776) (← links)
- Solving inverse problems using conditional invertible neural networks (Q2120777) (← links)
- On the antiderivatives of \(x^p/(1 - x)\) with an application to optimize loss functions for classification with neural networks (Q2122774) (← links)
- Robustness of LSTM neural networks for multi-step forecasting of chaotic time series (Q2122985) (← links)
- Recruitment-imitation mechanism for evolutionary reinforcement learning (Q2123550) (← links)
- DPM: a deep learning PDE augmentation method with application to large-eddy simulation (Q2123852) (← links)
- A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables (Q2124009) (← links)
- Trend to equilibrium for the kinetic Fokker-Planck equation via the neural network approach (Q2125428) (← links)
- Structure-preserving neural networks (Q2127014) (← links)
- SAMBA: safe model-based \& active reinforcement learning (Q2127227) (← links)
- Inclusion of domain-knowledge into GNNs using mode-directed inverse entailment (Q2127250) (← links)
- Generation of tubular and membranous shape textures with curvature functionals (Q2127269) (← links)
- Low-rank tensor reconstruction of concentrated densities with application to Bayesian inversion (Q2128063) (← links)
- PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain (Q2128357) (← links)
- Improving stateful premise selection with transformers (Q2128800) (← links)
- Solving inverse-PDE problems with physics-aware neural networks (Q2129334) (← links)
- A Helmholtz equation solver using unsupervised learning: application to transcranial ultrasound (Q2131029) (← links)
- Weak form theory-guided neural network (TgNN-wf) for deep learning of subsurface single- and two-phase flow (Q2131089) (← links)
- On obtaining sparse semantic solutions for inverse problems, control, and neural network training (Q2132578) (← links)
- Using neural networks to accelerate the solution of the Boltzmann equation (Q2132591) (← links)
- System identification through Lipschitz regularized deep neural networks (Q2132640) (← links)
- Deep-learning accelerated calculation of real-fluid properties in numerical simulation of complex flowfields (Q2132659) (← links)
- SPINN: sparse, physics-based, and partially interpretable neural networks for PDEs (Q2133032) (← links)
- Hybrid FEM-NN models: combining artificial neural networks with the finite element method (Q2133536) (← links)
- Physics-informed machine learning for reduced-order modeling of nonlinear problems (Q2133556) (← links)
- MIM: a deep mixed residual method for solving high-order partial differential equations (Q2133607) (← links)
- Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems (Q2133766) (← links)
- An FE-DMN method for the multiscale analysis of thermomechanical composites (Q2133887) (← links)
- Data-driven discovery of multiscale chemical reactions governed by the law of mass action (Q2134528) (← links)
- The mixed deep energy method for resolving concentration features in finite strain hyperelasticity (Q2134762) (← links)
