Introduction to Quantum Machine Learning (2019/2020)

Course code
cod wi: DT000225
Name of lecturer
Alessandra Di Pierro
Coordinator
Alessandra Di Pierro
Number of ECTS credits allocated
4
Academic sector
INF/01 - INFORMATICS
Language of instruction
Italian
Location
VERONA
Period
A.A. 19/20 dottorato dal Oct 1, 2019 al Sep 30, 2020.

Lesson timetable

Go to lesson schedule

Learning outcomes

The goal of this course is to show what benefits current and future quantum technologies can provide to machine learning, focusing on algorithms that are challenging with classical computers.
In particular, the students will be given the adequate notions and knowledge to be able to distinguish between quantum computing paradigms relevant for machine learning; identify problems in machine learning that would benefit from using quantum resources; implement learning algorithms on quantum computers using the available public platforms.

Syllabus

The course will award 4 CFU (16 hours frontal lectures).
The following is the list of topics that will be discussed.

• Introduction to Quantum Systems
• Quantum Computation
• Gate Model
• Adiabatic Quantum Computing
• Variational Circuits
• Classical-Quantum Learning Algorithms
• Encoding Classical Information
• Quantum-enhanced Kernel Methods
• Quantum-Assisted Learning Algorithms
• Practice:
Implementation of some of the discussed methods on real quantum computers using Qiskit (https://www.qiskit.org)
For this tutorial you will need to install Qiskit locally, which requires Python 3.5+. Although it isn't required, we recommend using a virtual environment with Anaconda.

CLASS SCHEDULE

21/9/2020 10:30 - 12:30
24/9/2020 10:30 - 12:30
25/9/2020 14.30 - 17.30
28/9/2020 14.30 - 17.30
29/9/2020 14.30 - 17.30
30/9/2020 14.30 - 17.30

Reference books
Author Title Publisher Year ISBN Note
Michael A. Nielsen, Isaac L. Chuang Quantum Computation and Quantum Information (Edizione 2) Cambridge University Press 2010 978-1-107-00217-3
Peter Wittek Quantum Machine Learning: What Quantum Computing Means to Data Mining (Edizione 1) Academic Press 2014 9780128009536
Maria Schuld, Francesco Petruccione Supervised Learning with Quantum Computers (Edizione 1) Springer, Cham 2018 978-3-319-96423-2

Assessment methods and criteria

Seminar on a topic in quantum machine learning