Neural networks in Fréchet spaces

DOI10.1007/s10472-022-09824-zOpenAlexW3204224161MaRDI QIDQ2679424

Fred Espen Benth, Nils Detering, Luca Galimberti

Publication date: 20 January 2023

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2109.13512

zbMATH Keywords

neural networksFréchet spaceuniversal approximationactivation function

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Nonlinear functional analysis (46T99)

Related Items

Pricing options on flow forwards by neural networks in a Hilbert space, Designing universal causal deep learning models: The geometric (Hyper)transformer

Uses Software

• DeepONet

Cites Work

• A basis theory primer.
• Stochastic partial differential equations. A modeling, white noise functional approach
• Multilayer feedforward networks are universal approximators
• The universal approximation property. Characterization, construction, representation, and existence
• The modern mathematics of deep learning
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• A proposal on machine learning via dynamical systems
• Functional data analysis.
• Interest rate models: an infinite dimensional stochastic analysis perspective
• A counterexample to the approximation problem in Banach spaces
• Neural Networks for Functional Approximation and System Identification
• Solving high-dimensional partial differential equations using deep learning
• Deep Neural Networks, Generic Universal Interpolation, and Controlled ODEs
• Error estimates for DeepONets: a deep learning framework in infinite dimensions
• Deep hedging
• Approximation by superpositions of a sigmoidal function
• Consistency problems for Heath-Jarrow-Morton interest rate models
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item