Résumé
Quantum Machine learning is a set of techniques developped recently to execute Machine learning models on quantum computers. Since the quantum computers begin to be effective in terms of computing power and error handling, they open a wide field of promising research. The machine learning has been developped for tenths of years now and there are a lot of challenges to adapt them to this new quantum technology. Since 2018, the first learning quantum circuit has been implemented and tested extensively, based on statistical techniques called kernel methods. But more recent developments give hope to access to more complicated models, similar to deep neural networks.
This talk exposes pedagogically the different prerequisites (machine learning, qubit mechanics, quantum computers) which are necessary to understand the subject. After that introduction, an overview of the different QML techniques will be explained in details, covering theoretical aspects as well as quantum programming of QML.
L'orateur
Ce webinaire sera présenté par Frédéric Magniette, ingénieur de recherche et chef de projet au LLR. Frédéric est responsable du sous-groupe "Quantum Machine Learning" du groupe de travail IN2P3 QC2I "Quantum Computing des 2 infinis".
Informations de connexion
Les informations de connexion seront fournies par e-mail sur la liste du RI3 la veille du webinaire (soit mercredi 11 mai).
Cellule évènement du RI3
