Pages that link to "Item:Q2401491"

The following pages link to A proposal on machine learning via dynamical systems (Q2401491):

Displaying 32 items.

• Deep neural network based adaptive learning for switched systems (Q6172098) (← links)
• Deep learning via dynamical systems: an approximation perspective (Q6172665) (← links)
• Pricing options on flow forwards by neural networks in a Hilbert space (Q6181517) (← links)
• Dynamical Systems–Based Neural Networks (Q6181900) (← links)
• Control of neural transport for normalising flows (Q6187083) (← links)
• Optimal control using to approximate probability distribution of observation set (Q6189711) (← links)
• Numerical Analysis for Convergence of a Sample-Wise Backpropagation Method for Training Stochastic Neural Networks (Q6190298) (← links)
• Optimal Dirichlet boundary control by Fourier neural operators applied to nonlinear optics (Q6196628) (← links)
• On mathematical modeling in image reconstruction and beyond (Q6200218) (← links)
• Efficient and stable SAV-based methods for gradient flows arising from deep learning (Q6497260) (← links)
• Global convergence in learning fully-connected ReLU networks via un-rectifying based on the augmented Lagrangian approach (Q6536825) (← links)
• A deep learning method for computing mean exit time excited by weak Gaussian noise (Q6539426) (← links)
• PottsMGNet: a mathematical explanation of encoder-decoder based neural networks (Q6541918) (← links)
• A data-driven framework for learning hybrid dynamical systems (Q6548679) (← links)
• Calibrating multi-dimensional complex ODE from noisy data via deep neural networks (Q6556771) (← links)
• On dynamical system modeling of learned primal-dual with a linear operator \(\mathcal{K}\): stability and convergence properties (Q6557695) (← links)
• An optimal control framework for adaptive neural ODEs (Q6561374) (← links)
• A dynamical systems approach to machine learning (Q6564359) (← links)
• Cell-average based neural network method for Hunter-Saxton equations (Q6578103) (← links)
• Operator learning using random features: a tool for scientific computing (Q6585281) (← links)
• A novel recurrent neural network of gated unit based on Euler's method and application (Q6610134) (← links)
• Mini-workshop: Nonlinear approximation of high-dimensional functions in scientific computing. Abstracts from the mini-workshop held October 15--20, 2023 (Q6613392) (← links)
• Vanilla feedforward neural networks as a discretization of dynamical systems (Q6645925) (← links)
• Neural dynamical operator: continuous spatial-temporal model with gradient-based and derivative-free optimization methods (Q6648386) (← links)
• NINNs: Nudging induced neural networks (Q6650078) (← links)
• Training neural networks from an ergodic perspective (Q6655492) (← links)
• Predict globally, correct locally: parallel-in-time optimization of neural networks (Q6659267) (← links)
• Inverse evolution layers: physics-informed regularizers for image segmentation (Q6664476) (← links)
• Double-well net for image segmentation (Q6669799) (← links)
• A generalized framework of neural networks for Hamiltonian systems (Q6670713) (← links)
• Constrained dynamics, stochastic numerical methods and the modeling of complex systems. Abstracts from the workshop held May 26--31, 2024 (Q6671623) (← links)
• Adaptive deep density approximation for stochastic dynamical systems (Q6671865) (← links)