Deep learning without global optimization by random Fourier neural networks
From MaRDI portal
Cites work
- A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- An adaptive Metropolis algorithm
- Bridging traditional and machine learning-based algorithms for solving PDEs: the random feature method
- Classical Fourier Analysis
- Deep learning
- Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
- Galerkin neural networks: a framework for approximating variational equations with error control
- Julia: a fresh approach to numerical computing
- Optimal scaling for various Metropolis-Hastings algorithms.
- Smaller generalization error derived for a deep residual neural network compared with shallow networks
- Stacked networks improve physics-informed training: applications to neural networks and deep operator networks
- The Random Feature Method for Time-Dependent Problems
- Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks
- Understanding machine learning. From theory to algorithms
- Universal approximation bounds for superpositions of a sigmoidal function
- When and why PINNs fail to train: a neural tangent kernel perspective
This page was built for publication: Deep learning without global optimization by random Fourier neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7013718)
