Course - Machine Learning - TDT4173
TDT4173 - Machine Learning
Examination arrangement: Portfolio
Grade: Letter grades
|Evaluation||Weighting||Duration||Grade deviation||Examination aids|
The course gives an introduction to the principles and methods for automatic learning in computer systems. Classical syntax-based learning methods as well as more knowledge-intensive methods are described. Main empahsis is on symbolic methods, where explicit concepts and relationships are learned. Statistical generalizations, time series methods, ensemble methods, and deep learning are also included. The strengths and weaknesses of various methods are discussed. Learning methods in case-based reasoning is integrated with problem solving within the CBR cycle. Numerical and cognitive models for similarity asessment will be discussed, together with different learning system architectures. Methods that combine case-based and generalisation-based inferences will be discussed as well.
The aim of the course is to introduce principles of machine learning methods in general, to give an understanding of basic mechanisms underlying various specific methods. In case-based reasoning the integration of learning and problem solving is focused.
Learning methods and activities
Lectures, group work, colloquia and self study.
Further on evaluation
The course evaluation includes two parts. (1) Every student must first pass an individual assignment (IA) about one month after the course begins. Each student can get a second attempt to pass the IA, but the student will receive a deduction (-5%) in the course points. Students who fail the IA for both attempts will receive an F or Fail course grade. (2) Only those who pass the IA can continue to the course project. The project is graded for the whole team (each team comprises up to three students). The project points equal base points (max. 100% and min. 41%) plus potential project deductions (from 0% to -17%). The base points are proportional to the number of Virtual Teams (VTs) defeated by the student team in terms of prediction performance. The teachers and teaching assistants prepare the VTs. If a student team cannot defeat any VT, the team members will fail the project and thus the course. The potential deductions include a late submission (within three days) and failure to document key components in machine learning practice.
The course points will then be rounded to a letter grade according to the NTNU standard ranges. If the student receives an F or Fail as a final grade, the student must retake the whole course.
Recommended previous knowledge
TDT4136 Introduction to Artificial Intelligence, TDT4171 Artificial Intelligence Methods or similar.
- Tom Mitchell: Machine learning, McGraw Hill, 1997.
- Michael M. Richer and Rosina Weber: Case-Based Reasoning, Springer, 2013.
Credits: 7.5 SP
Study level: Second degree level
Term no.: 1
Teaching semester: AUTUMN 2022
Language of instruction: English
- Industrial Economics
- Information Security
- Technological subjects
Department with academic responsibility
Department of Computer Science
Examination arrangement: Portfolio
- Term Status code Evaluation Weighting Examination aids Date Time Examination system Room *
- Autumn ORD Portfolio 100/100
Room Building Number of candidates
- * The location (room) for a written examination is published 3 days before examination date. If more than one room is listed, you will find your room at Studentweb.
For more information regarding registration for examination and examination procedures, see "Innsida - Exams"