Machine Learning Quantum and Classical

Welcome to the course of Machine learning quantum and classical of the master in quantum science and technology in Barcelona!

Course and Documentation

Course Description

This course gives an introduction to machine learning and to deep neural networks: from linear linear models to generative models. We will cover the following topics: - Linear Models (linear regression, polynomial regression and logistic regression) - Deep Neural networks - Convolutional Neural Networks - Restricted Boltzmann Machines - Generative Models

The course combines theory and practice. In particular, we have prepared jupyter notebooks in python and with the use of specific librairies such as numpy, Pytorch and fastai.

Syllabus

Date	Lecture	Lecturer
13/12	Introduction + Linear models	Alexandre Dauphin
15/12	Linear models	Alexandre Dauphin
20/12	Linear models + Introduction to neural networks	Alexandre Dauphin
22/12	Probabilistic view on Machine Learning	Alexandre Dauphin
10/02	Practical introduction to Neural Networks	Borja Requena
12/01	Neural Network fundamentals: Implementation from scratch	Marcin Płodzień
17/01	Neural Network fundamentals: Automatic differentiation	Marcin Płodzień
19/01	Neural Network fundamentals: Convolutional neural networks and regularization techniques	Marcin Płodzień
24/01	Introduction to classical Monte Carlo and sampling	Paolo Stornati
26/01	Restricted Boltzman machines	Paolo Stornati
31/01	Generative models	Borja Requena
02/02	Overiew of the state of the art and Applications in Physics	Borja Requena

Instructors

Alexandre Dauphin

Borja Requena

Marcin Płodzień

Paolo Stornati