Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
Basics of machine learning
Anna Dawid (University of Warsaw), Julian Arnold (University of Basel), Borja Requena (Institute of Photonic Sciences), Alexander Gresch (Heinrich Heine University Düsseldorf), Marcin Płodzień (Institute of Photonic Sciences), Kaelan Donatella (Université Paris Diderot), Kim A. Nicoli (University of Bonn), Paolo Stornati (Institute of Photonic Sciences), Rouven Koch (Aalto University), Miriam Büttner (University of Freiburg), Robert Okuła (Gdańsk University of Technology), Gorka Muñoz-Gil (Universität Innsbruck), Rodrigo A. Vargas-Hernández (McMaster University), Alba Cervera-Lierta (Barcelona Supercomputing Center), Juan Carrasquilla (ETH Zurich), Vedran Dunjko (Leiden University), Marylou Gabrié (Institut Polytechnique de Paris), Patrick Huembeli, Evert van Nieuwenburg (Leiden University), Filippo Vicentini (Institut Polytechnique de Paris), Lei Wang (Chinese Academy of Sciences), Sebastian J. Wetzel (University of Waterloo), Giuseppe Carleo (École Polytechnique Fédérale de Lausanne), Eliška Greplová (Delft University of Technology), Roman V. Krems (University of British Columbia), Florian Marquardt (Max Planck Society, Max Planck Institute for the Science of Light), Michał Tomza (University of Warsaw), Maciej Lewenstein (Institute of Photonic Sciences), Alexandre Dauphin (Institute of Photonic Sciences)
Résumé : In this chapter, we describe basic machine learning concepts connected to optimization and generalization. Moreover, we present a probabilistic view on machine learning that enables us to deal with uncertainty in the predictions we make. Finally, we discuss various basic machine learning models such as support vector machines, neural networks, autoencoders, and autoregressive neural networks. Together, these topics form the machine learning preliminaries needed for understanding the contents of the rest of the book.