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

DOI10.13164/ma.2022.07OpenAlexW3193780612WikidataQ114056961 ScholiaQ114056961MaRDI QIDQ5048595

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

cross validationsupport vector machinedeep neural networkssingle hidden layer neural networkskernel learning machines

Mathematics Subject Classification ID

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

Uses Software

• Kernlab
• ImageNet
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Principles and theory for data mining and machine learning
• Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
• Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation
• Multilayer feedforward networks are universal approximators
• Support-vector networks
• Bayesian learning for neural networks
• Dropout fails to regularize nonparametric learners
• Approximation and learning by greedy algorithms
• Universal approximation bounds for superpositions of a sigmoidal function
• An empirical demonstration of the no free lunch theorem
• On the ubiquity of the Bayesian paradigm in statistical machine learning and data science
• Model Selection for Optimal Prediction in Statistical Machine Learning
• Kernelized cost-sensitive listwise ranking
• Approximation by superpositions of a sigmoidal function

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