Login for PhD students/staff at UCPH      Login for others
Machine Learning for SCIENCE (MLS)
Provider: Faculty of Science

Activity no.: 5182-23-02-31 
Enrollment deadline: 15/05/2023
PlaceDepartment of Computer Science
Date and time22.05.2023, at: 09:00 - 26.05.2023, at: 16:00
[antalgange]5
Regular seats55
ECTS credits4.00
Contact personErik Bjørnager Dam    E-mail address: erikdam@di.ku.dk
Enrolment Handling/Course OrganiserErik Bjørnager Dam    E-mail address: erikdam@di.ku.dk
Written languageEnglish
Teaching languageEnglish
Semester/BlockBlock 4
Scheme group notePlenum teaching will be done for five consecutive days from 9 to 16.
Exam requirementsExam details The student writes a synopsis outlining a possible analysis applying some of the course methodology, ideally on their own data.
Exam formWritten assignment
Grading scalePassed / Not passed
Exam re-examinationExam re-examination If the student synopsis is not approved, the student has the possibility of resubmission based on the feedback from the examination.
Course workload
Course workload categoryHours
Course Preparation5.00
Lectures15.00
Theory exercises20.00
Project work30.00
Exam10.00
Sum80.00
Enrolment guidelines
The Machine Learning for SCIENCE (MLS) course introduces key analysis methods in Machine Learning. These methods allow investigations of scientific data from most fields, including data from physical measurements, questionnaires, pictures, internet searches, satellites, and biochemical outcomes. We cover data cleaning (e.g. missing data, denoising), feature extraction, machine learning basics (labels, variables, parameter optimization, overfitting, cross-validation), key machine learning and image analysis methods based on both unsupervised and supervised learning, and visualization. Method-wise, we start at Linear Discriminant Analysis and end with Deep Learning.
At the end of the course, the students must write a synopsis with a suggestion for an analysis ideally performed on their own data including a small implementation of a key concept. This synopsis could form the basis for the Data Science Projects PhD course also offered by the Data Science Lab.

Formal requirements
The number of participants is limited at 50, and priority will be given to PhD students from UCPH-SCIENCE and participants is a previous Data Science Lab course (Introduction to Python or R, Statistical Methods I).
We assume that the students have some experience with Python programming.

Learning outcome
After course completion the students are expected to be able to:

Knowledge:
- Understand key machine learning concepts (parameter training, overfitting).
- Understand key machine learning methods (LDA, (un-) supervised learning).
- Understand key image analysis methods (e.g. feature extraction).

Skills:
- Develop/adapt/extend a computer-based software method for analysis of relevant data.
Competences:
- Propose relevant analysis methods for scientific data science problems.
- Consider cross-disciplinary data science methods in their research.

Literature
Course lecture slides and exercises.
We will use data, examples, and other material from publicly available sources.

Teaching and learning methods
The course is composed of sessions combining lectures and exercises. For each topic, the students will get hands-on experience in applying, modifying, and programming analysis methods.
The programming examples will be implemented using Python in JupyterLab notebooks.

Lecturers
Erik Dam and Stefan Oemhcke

Remarks
Examination:
The students need to hand in their synopsis (10 days after the final course day). The synopsis must be approved. The students are allowed to work in 2-person groups.

PARTICIPATION FEE:
PhD students enrolled at the PhD School of SCIENCE are exempt from the participation fee.
All other students are required to pay the participation fee of DKK 4.500.

Details and Updates:
For details for this and other Data Science Lab courses, see: http://datalab.science.ku.dk/english/course/

Search
Click the search button to search Courses.


Course calendar
See which courses you can attend and when
JanFebMarApr
MayJunJulAug
SepOctNovDec