Complexity of shallow networks representing finite mappings

DOI10.1007/978-3-319-19324-3_4MaRDI QIDQ2814145zbMATH OpenOpenAlexFDO

Authors Věra Kůrková

Publication date 17 June 2016

Published in Artificial Intelligence and Soft Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-319-19324-3_4

zbMATH Keywords

model complexityHadamard matricesfinite mappingsshallow feedforward networkssignum perceptrons

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Boolean and Hadamard matrices (15B34)

Recommendations

• Probabilistic lower bounds for approximation by shallow perceptron networks
• On the capabilities of multilayer perceptrons
• scientific article; zbMATH DE number 109318
• Limitations of shallow nets approximation
• scientific article; zbMATH DE number 903397

Cites work

• scientific article; zbMATH DE number 109318 (Why is no real title available?)
• scientific article; zbMATH DE number 3482343 (Why is no real title available?)
• scientific article; zbMATH DE number 773997 (Why is no real title available?)
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• A Fast Learning Algorithm for Deep Belief Nets
• A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
• Complexity estimates based on integral transforms induced by computational units
• Complexity of Gaussian-radial-basis networks approximating smooth functions
• Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks
• Enumeration of Seven-Argument Threshold Functions
• Feedforward Neural Network Methodology
• Interpolation of scattered data: distance matrices and conditionally positive definite functions
• Learning deep architectures for AI
• Lower bounds for approximation by MLP neural networks
• On best approximation by ridge functions

Cited in

(4)

• Vulnerability of classifiers to evolutionary generated adversarial examples
• Expressivity of Deep Neural Networks
• On the complexity of loading shallow neural networks
• Any target function exists in a neighborhood of any sufficiently wide random network: a geometrical perspective

This page was built for publication: Complexity of shallow networks representing finite mappings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2814145)