Login for PhD students/staff at UCPH      Login for others
Machine Learning and Imaging Projects
Second title: PhD course
Provider: Faculty of Science

Activity no.: 5178-19-02-32 
Enrollment deadline: 18/09/2019
PlaceDepartment of Computer Science
Universitetsparken 1, 2100 København Ø
Date and time24.09.2019, at: 00:00 - 12.11.2019, at: 00:00
[antalgange]8
Regular seats20
ECTS credits4.50
Contact personAnnette Lange    E-mail address: alange@di.ku.dk
Enrolment Handling/Course OrganiserAnnette Lange    E-mail address: alange@di.ku.dk
Written languageEnglish
Teaching languageEnglish
Semester/BlockBlock 1
Exam requirementsThe students need to hand in their report and present their work at the final course day. Both report and oral presentation must be approved. The students are allowed to work and present in 2-person groups (3-person groups may be allowed in exceptional ca
Exam formA report on an agreed topic followed by an oral presentation
Grading scalePassed / Not passed
Exam re-examinationIf the student did not pass based on the written report and the oral defense, then the student has the possibility of resubmitting the report based on the feedback from the examination. The resubmitted report then has to be sufficiently elaborate by itself in order to pass the reevaluation.

Content
 

With increasing interest in applying Machine Learning methods in different domains, this course provides a platform to develop and work on projects with the student’s own data using Machine Learning methods, with supervisory support from the course teachers. The data sources can range from pictures, scans, videos or graphs to tabulated measurements in text or digital formats; all related to some scientific investigation. Ideally, the size and complexity of the data is such that manual analysis is either not feasible or tedious to perform. Typical analysis within the scope of this course could be automated quantification of objects or quantities of interests in the data (for example, image analysis), or combining different types of data to address a common research question (like combining text and images), or building predictive models using Machine Learning. The course output will be a manuscript written like a research paper – that will ideally be submitted to a journal following the course. 

No later than 2 weeks prior to the course, the participants should submit a synopsis with a short description of the data and the desired outcome. This will allow us to consider whether to plan plenum lectures on some specific analysis method. 


Formel requirements

We invite PhD students from all SCIENCE departments, but some experience with programming is required. The number of participants is limited to 20, and priority will be given to students who previously followed another Data Science Lab course (Introduction to Python or R, Statistical Methods I, and particularly Machine Learning and Imaging Methods).


Learning outcome

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

Knowledge:
- Describe the analysis methods used by others for similar problems.

- Describe relevant, alternative approaches for solving the problem.
Skills:
- Develop/adapt/extend a computer-based software method for quantification and/or analysis of their own data. 

Compentences:

- Formulate scientific questions from their PhD project in terms of research hypotheses.
- Interpret the results of their computer-based analysis in relation to their PhD project.


Literature

This depends on the individual project.

For potential background literature, see the course pages for the Introduction to Python, Introduction to R, Statistical Methods for the Biosciences I, and particularly Machine Learning and Imaging Methods


Teaching and learning methods

The course days include traditional lectures but will to a large degree be a workshop setting where the students work with their projects with the lecturers available for help, feedback, and suggestions. The participants will also have individual supervision meetings with the course lecturers. The projects must result in research article style reports and be presented before the entire class at the concluding examination seminar. The projects may be done using software packages of the participant’s own choice. The lecturers have particular experience with the software frameworks Python and Matlab.


Lecturers
Erik Bjørnager Dam    erikdam@diku.dk      and  Selvan Raghavendra  raghav@di.ku.dk

Workload

Course workload category Hours
Course Preparation                                  7.00
Lectures                                               12.00
Theory exercises                                     6.00
Project work                                         90.00
Exam                                                     6.00
_____________________________________
Sum                                                    123.00
             

 
   
   
   
   
   
 
   

Content

With increasing interest in applying Machine Learning methods in different domains, this course provides a platform to develop and work on projects with the student’s own data using Machine Learning methods, with supervisory support from the course teachers. The data sources can range from pictures, scans, videos or graphs to tabulated measurements in text or digital formats; all related to some scientific investigation. Ideally, the size and complexity of the data is such that manual analysis is either not feasible or tedious to perform. Typical analysis within the scope of this course could be automated quantification of objects or quantities of interests in the data (for example, image analysis), or combining different types of data to address a common research question (like combining text and images), or building predictive models using Machine Learning. The course output will be a manuscript written like a research paper – that will ideally be submitted to a journal following the course. 

No later than 2 weeks prior to the course, the participants should submit a synopsis with a short description of the data and the desired outcome. This will allow us to consider whether to plan plenum lectures on some specific analysis method. 


Search
Click the search button to search Courses.


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



Publication of new courses
All planned PhD courses at the PhD School are visible in the course catalogue. Courses are published regularly.