Pages that link to "Item:Q5001377"

The following pages link to Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences (Q5001377):

Displayed 11 items.

• A physics-informed multi-fidelity approach for the estimation of differential equations parameters in low-data or large-noise regimes (Q2075654) ‎ (← links)
• Compliance minimisation of smoothly varying multiscale structures using asymptotic analysis and machine learning (Q2142133) ‎ (← links)
• Higher-Order Quasi-Monte Carlo Training of Deep Neural Networks (Q5015302) ‎ (← links)
• A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations (Q5058646) ‎ (← links)
• Deep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty Quantification (Q5097855) ‎ (← links)
• Finite Neuron Method and Convergence Analysis (Q5162357) ‎ (← links)
• On the approximation of functions by tanh neural networks (Q6055124) ‎ (← links)
• Physics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithms (Q6087958) ‎ (← links)
• Convergence Analysis of a Quasi-Monte CarloBased Deep Learning Algorithm for Solving Partial Differential Equations (Q6151262) ‎ (← links)
• wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws (Q6197777) ‎ (← links)
• Approximation bounds for convolutional neural networks in operator learning (Q6403941) ‎ (← links)