On some similarities and differences between deep neural networks and kernel learning machines

DOI10.13164/MA.2022.07MaRDI QIDQ5048595zbMATH OpenOpenAlexWikidataFDO

Authors Eddie Pei, Ernest Fokoué

Publication date 16 November 2022

Published in Mathematics for Application (Search for Journal in Brave)

Full work available at URL https://doi.org/10.13164/ma.2022.07

zbMATH Keywords

support vector machinecross validationdeep neural networkskernel learning machinessingle hidden layer neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computational aspects of data analysis and big data (68T09) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Recommendations

• On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces
• When do neural networks outperform kernel methods?*
• Performance comparisions of neural networks and machine learning techniques: A critical assessment of the methodology
• Deep vs. shallow networks: an approximation theory perspective
• Publication:4943029

Cites work

• scientific article; zbMATH DE number 45848 (Why is no real title available?)
• scientific article; zbMATH DE number 795573 (Why is no real title available?)
• An empirical demonstration of the no free lunch theorem
• Approximation and learning by greedy algorithms
• Approximation by superpositions of a sigmoidal function
• Bayesian learning for neural networks
• Deep learning
• Dropout fails to regularize nonparametric learners
• Kernelized cost-sensitive listwise ranking
• Model Selection for Optimal Prediction in Statistical Machine Learning
• Multilayer feedforward networks are universal approximators
• Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
• On the ubiquity of the Bayesian paradigm in statistical machine learning and data science
• Preface: The multifaceted impact of statistical methodology and theory in data science
• Principles and theory for data mining and machine learning
• Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation
• Support-vector networks
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(1)

• On Kernel Method–Based Connectionist Models and Supervised Deep Learning Without Backpropagation

Describes a project that uses

Uses Software

• AlexNet
• ImageNet
• Kernlab

This page was built for publication: On some similarities and differences between deep neural networks and kernel learning machines

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5048595)