Quantum Machine Learning course
Stéphane Vialle, Professor at CentraleSupelec Damien Rontani, Professor at CentraleSupelec
Stephane.Vialle@centralesupelec.fr Damien.Rontani@centralesupelec.fr
Julien Rauch, PhD student Thibaud Ardant, PhD student
Course theme and objectives :
This course presents the main concepts and algorithms of quantum ML based on quantum circuits for digital architectures and introduces some methods of quantum ML algorithms on analog architectures.
Firstly, the course introduces embedding techniques in Hilbert space and some mechanisms for computing gradients or alternative solutions. Based on these mechanisms, the course presents various quantum algorithms for data clustering, neural networks and generative networks. Built around variational quantum algorithms and quantum circuits, they can run on digital current NISQ or future FTQC architectures to perform classifications or predictions.
Finally, the course introduces some quantum algorithms mainly designed for analog quantum architectures: QUBO optimization methods used to train some ML models and quantum reservoir algorithms.
Knowledge of quantum circuit programming is assumed, including Variational Quantum Algorithm. Knowledge of classical ML will be useful, but reminders will be given at the beginning of courses that require it.
Course outline:
Part I: Principles and basic mechanisms
QML introduction: from ML to Quantum ML
Quantum encoding methods
Quantum embedding & Feature Maps
Part II: QML based on VQA and quantum circuits
VQA & Feature Maps
Quantum data clustering
Quantum Neural Networks
Quantum generative networks
Parallel circuits of neural networks
Part III: QML on analog quantum architectures
Quantum reservoirs
Supports de cours (slides, TD et TP) :