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

De Zarzà, I.

Softcover

ISBN 10: 620392539X ISBN 13: 9786203925395

Verlag: LAP LAMBERT Academic Publishing, 2021

Inhaltsangabe

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>

Über diesen Titel

Über die Autorin bzw. den Autor

I. de Zarzà graduated in Mathematics at Universitat Autònoma de Barcelona and Universitat de Barcelona where she specialized in pure mathematics and telecommunications. De Zarzà has done further graduate studies in Electrical Engineering and Computer Science at City University of Hong Kong and at Carnegie Mellon, as well as at ETH Zürich.

Details zur Ausgabe

• Verlag: LAP LAMBERT Academic Publishing
• Erscheinungsdatum: 2021
• Sprache: Englisch
• ISBN 10: 620392539X
• ISBN 13: 9786203925395
• Einband: Taschenbuch
• Anzahl der Seiten: 76
• Kontakt zum Hersteller: Nicht verfügbar
• Verantwortliche Person: JustFiction Edition; customerservice@vdm-vsg.de; ; Brivibas gatve 197; Riga; 1039; Lettland