Fast Kernel Expansions with Applications to CV and DL. Part 1b: Carnegie Mellon. City University of Hong Kong - Couverture souple

De Zarzà, I.

Couverture souple

ISBN 10 : 620392539X ISBN 13 : 9786203925395

Editeur : LAP LAMBERT Academic Publishing, 2021

Synopsis

The scope of the manuscript is to give a review of kernel expansions, FOURIER features and fast numerical code in statistical learning. For this purpose we introduce a library for approximating kernel expansions, which enables the use of kernel methods in large-scale datasets. It is well-known that kernel methods as originally proposed are computational costly for big data, we explain here the theory needed to enable the use of non-linear features in log-linear time. This approximation is based on FOURIER features by the use of the Walsh Hadamard. A SIMD implementation of the algorithm is described. Applications to Computer Vision (CV) and Deep Learning (DL) are enclosed with practical hints on the topic. Specifically, we give a primer on facial recognition and a foundation for the use of Vision in Robotics. <div><p style="text-align: justify;">The scope of the manuscript is to give a review of kernel expansions, FOURIER features and fast numerical code in statistical learning. For this purpose we introduce a library for approximating kernel expansions, which enables the use of kernel methods in large-scale datasets. It is well-known that kernel methods as originally proposed are computational costly for big data, we explain here the theory needed to enable the use of non-linear features in log-linear time. This approximation is based on FOURIER features by the use of the Walsh Hadamard. A SIMD implementation of the algorithm is described. Applications to Computer Vision (CV) and Deep Learning (DL) are enclosed with practical hints on the topic. Specifically, we give a primer on facial recognition and a foundation for the use of Vision in Robotics. </p></div>

Détails de l'édition

• Éditeur: LAP LAMBERT Academic Publishing
• Date d'édition: 2021
• Langue: anglais
• ISBN 10: 620392539X
• ISBN 13: 9786203925395
• Reliure: Broché
• Nombre de pages: 76
• Coordonnées du fabricant: non disponible
• Personne responsable: KreGa Onlinehandel GmbH; 4950000000000; info@krega-onlinehandel.de; ; Birkenweg 31; Brakel; 33034; Allemagne