QC810: Quantum Machine Learning

Entry requirements

Entry requirements: None

Academic preconditions

Students following the course are expected to be acquainted with the contents of the following courses:

Introduction to Quantum Computing.
Familiarity of machine learning, linear algebra, statistic and programming language like python is recommended but not required.

Course introduction

The last two decades have witnessed a technological revolution across diverse sectors driven by machine learning. However, classical computers are reaching their limits as the complexity of these algorithms grows exponentially, often requiring the training of billions of parameters. In recent years, researchers have explored the potential of quantum computing to enhance classical machine learning. This course bridges the cutting-edge fields of quantum computing and machine learning, providing both the theoretical foundations and practical skills needed for success in this emerging domain, along with hands-on experience in coding and applying these methods to real-world problems.

Expected learning outcome

The learning objective of the course is that the student demonstrates at the exam mastery of

Basic concepts and terminology introduced in the course.
Foundational methods, results, and principles of quantum machine learning theory.
Implementation of quantum training on real-world case study.

Content

This course will cover a selection of the following topics

The essential mathematical and statistical principles behind machine learning.
Key machine learning algorithms and their quantum counterparts.
Practical applications of quantum machine learning.

Literature

Frank Zickert, Hands-On Quantum Machine Learning With Python: Volume 1 and 2, Amazon Digital Services LLC - KDP Print US

Jacob Biamonte et al. Quantum machine learning. In: Nature 549 (7671 Sept. 2017), pp. 195–202. doi:10.1038/nature23474.

Examination regulations

Exam element a)

Timing

Spring and June

Tests

Portfolio

EKA

N310094102

Assessment

Second examiner: Internal

Grading

7-point grading scale

Identification

Full name and SDU username

Language

English

Duration

Oral exam - 15 minutes, 10 minutes for presentation and 5 minutes for questions

Examination aids

Project report - All common aids allowed
Oral exam - No aids allowed

ECTS value

Additional information

Portfolio consisting of the following elements:

Written assignment in the form of a project report, written in small groups during the second half of the course
Final oral exam in the form of an individual project defense during the exam period

To achieve a passing grade overall, both elements 1 and 2 must individually meet the learning objectives.

The assessment of element 1 takes place in conjunction with the completion of element 2.
Element 1 contributes 50% to the final grade, and element 2 contributes 50%. However, an overall assessment is applied.

Indicative number of lessons

70 hours per semester

Teaching Method

Planned lessons:

Total number of planned lessons: 70

Hereof:

Common lessons in classroom/auditorium: 42

Team lessons in classroom: 28

During the common lessons, there will be lectures and group work. During the team lessons, there will be exercise solving, student presentations and group work.

Other planned teaching activities:

Outside of the planned lessons, there will be self study (including preparation for lessons and the exam) as well as work in a projec in small groups.

Teacher responsible

Name	E-mail	Department
Matthias Oliver Wilhelm	mwilhelm@imada.sdu.dk	Institut for Matematik og Datalogi

Timetable

Odense

Show full time table (start E25)
Show full time table (start F26)

Administrative Unit

Institut for Matematik og Datalogi (matematik)

Team at Registration

NAT

Offered in

Odense

Recommended course of study

Profile	Education	Semester	Offer period

Transition rules

Transitional arrangements describe how a course replaces another course when changes are made to the course of study.

If a transitional arrangement has been made for a course, it will be stated in the list.

See transitional arrangements for all courses at the Faculty of Science.