Reconstructing a neural net from its output

DOI10.4171/RMI/160zbMATH Open0877.68098OpenAlexW2017834428MaRDI QIDQ1344572FDOQ1344572

Authors Charles Fefferman 

Publication date 8 December 1997

Published in Revista Matemática Iberoamericana (Search for Journal in Brave)

Full work available at URL https://eudml.org/doc/39464

zbMATH Keywords

neural nets

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cited In (25)

• A mathematical solution to a network construction problem.
• Harmonic functions on the closed cube: an application to learning theory
• Ehresmann connections and feedforward neural networks
• On the identification of neural responses
• Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples
• Neural network identifiability for a family of sigmoidal nonlinearities
• Robust and resource-efficient identification of two hidden layer neural networks
• How to modify a neural network gradually without changing its input-output functionality
• Affine symmetries and neural network identifiability
• Title not available (Why is no real title available?)
• Neural networks as set-valued dynamical systems and the universality of the windowed Fourier transform
• Title not available (Why is no real title available?)
• Absence of bottlenecks in a neural network determines its generic functional properties
• Metric entropy limits on recurrent neural network learning of linear dynamical systems
• Using neural nets for eliminating noise in experimental signals
• Neural networks, rational functions, and realization theory
• Parameter identifiability of a deep feedforward ReLU neural network
• Identifying linear combinations of ridge functions
• Information theory and recovery algorithms for data fusion in Earth observation
• Title not available (Why is no real title available?)
• Polynomial time cryptanalytic extraction of neural network models
• Higher-order quasi-Monte Carlo training of deep neural networks
• Construction of neural networks for determination of singular points of linear complexes of planes of category B
• On partial groupoids associated with the composition of multilayer feedforward neural networks
• An embedding of ReLU networks and an analysis of their identifiability

This page was built for publication: Reconstructing a neural net from its output

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1344572)