Study Guide@lith
 

Linköping Institute of Technology

 
 
Valid for year : 2017
 
TDDE19 Advanced Project Course - AI and Machine Learning, 6 ECTS credits.
/Avancerad projektkurs: AI och maskininlärning/

For:   CS   D   DAV   IT   U  


OBS!

The course is not available for exchange students

 

Prel. scheduled hours: 64
Rec. self-study hours: 96

  Area of Education: Technology

Main field of studies: Computer Science, Computer Engineering

  Advancement level (G1, G2, A): A

Aim:
The project should have significant technical level that requires in-depth subject knowledge in artificial intelligence and machine learning, should be carried out in a professional manner, and should develop and consolidate the participants' skills in the following areas:
  • Analyze and structure problems in the area of artificial intelligence and machine learning.
  • Apply knowledge and methods from a wide range of previous courses in the areas of artificial intelligence and machine learning.
  • Independently acquire new knowledge, as required by the project.
  • Integrate knowledge from many disciplines and apply them in the context of artificial intelligence and machine learning.
  • Formulate a requirement specification for the project based on a project directive and thereby assess the feasibility of the project in terms of technical solutions and available resources.
  • Present the project results for teh client as well as for other students, which can not be presumed to be specialists in the techniques used.
  • Actively contribute to a well functioning project group.
  • Demonstrate the ability to lead the project work with the support of a project model, and with limited access to supervisory resources.
  • Plan, implement and monitor a project in the area of artificial intelligence and machine learning.
The result of the project work should:
  • Attain high technical quality and be based on modern knowledge and practices in the relevant field of technology.
  • Be documented in relevant project documents and relevant technical documentation.
  • Be presented orally.
  • Meet the requirements stated in the specification.


Prerequisites: (valid for students admitted to programmes within which the course is offered)
The course expects the student to have applied project management models in previous courses or other context. The student should also have acquired knowledge equivalent to basic courses in the profile "AI and machine learning" or the specialization "AI and data mining" in the area covered by the project.

Note: Admission requirements for non-programme students usually also include admission requirements for the programme and threshhold requirements for progression within the programme, or corresponding.

Organisation:
The project, which is formed according to directive given later, should consist of at least six students. Each group will be assigned a supervisor, who will support the group in its work and answer technical questions. For each project, there is a client with whom the project team negotiates a specification. Before project work begins, the project team should create appropriate project management documents for the project.
For each instance of the course, the examiner will present a set of project proposals. Assignment of projects to student groups is based both on their aptitude and their wishes. For each proposal there is a project charter forming the basis for further work. The project begins with the project team developing a requirements specification and relevant project management documentation for their project. The projects should be conducted according to an appropriate development model, selected by the team.
The course runs over the entire autymn semester.


Course contents:
Description of the projects, with project directives, are available on the course website. The projects will be closely linked to either ongoing research within the field of computer science or to companies active in this field. Examples could be develop a robotic system to perform some specific type of tasks, develop a system that learns to detect and track objects from sensor data, develop a recommender system for a specific domain, develop a system that learns to predict the activity of an object based on prior observations. The nature of the projects may change from year to year.

Course literature:
Specific to the project.

Examination:
Project
6 ECTS
 
The project work will be assessed on the achievement of course objectives. Three modules, each assessed with pass/fail, are included in the assessment. These topics are:
  • Technical level and quality of project results
  • Written documentation in the form of technical report and relevant project documents
  • Oral presentation
To pass the whole project work, the student is required to pass all parts and meet the objectives of the course. Special emphasis is given to participants actively contributing to the group working according to the project model's intentions.
Grades are given as �?�Fail�?� or �?�Pass�?�.



Course language is English.
Department offering the course: IDA.
Director of Studies: Peter Dalenius
Examiner: Cyrille Berger

Course Syllabus in Swedish

Linköping Institute of Technology

 


Contact: TFK , val@tfk.liu.se
Last updated: 03/09/2017