Machine Learning and Data Mining

Professor in charge: Samuel Kaski
Extent: Long major (55-65 credits). Compact major is not offered. Students who want to take a minor are encouraged to include it in elective studies.
Abbreviation: Macadamia
Code: SCI3044
School: School of Science

Objectives

The major in Machine Learning and Data Mining (Macadamia) gives a strong basic understanding of modern computational data analysis and modelling methodologies. It builds on the strong research at the Department of Computer Science. The methods of machine learning and data mining are applicable and needed in a wide variety of fields ranging from process industry to mobile communications and social networks. Recent spearhead application areas include bioinformatics, computational linguistics, multimodal interfaces, and intelligent information access. The major provides an excellent basis for doctoral studies as well as industrial research and development work. Teaching and supervision for Macadamia students is given by an enthusiastic and experienced group headed by world leaders in this research field. Excellent Macadamia students can continue their studies in the Helsinki Doctoral Education Network in Information and Communication Technology (HICT).

Learning Outcomes

1) The student is able to formalize data analysis problems in terms of the underlying statistical and computational principles

2) The student is able to assess suitability of different machine learning methods for solving a particular new problem encountered in industry or academia, and apply the methods to the problem.

3) The student can interpret the results of a machine learning algorithm, assess their credibility, and communicate the results with experts of other fields.

4) The student can implement common machine learning methods, and design and implement novel algorithms by modifying the existing approaches.

5) The student understands the theoretical foundations of the machine learning field to the extent required for being able to follow research in the field

Content and Structure

The students have to take the eight compulsory courses. In addition, they include courses from the major optional courses list. Also other optional courses may be included per agreement with a professor in charge of the major.

Major compulsory courses 45 credits

CODE	NAME	CREDITS	PERIOD/YEAR
CS-E3210	Machine Learning: Basic Principles	5	I/1st year
CS-E5710	Bayesian Data Analysis	5	I-II/1st year
CS-E4810	Machine Learning and Neural Networks	5	II/1st year
CS-E4820	Machine Learning: Advanced Probabilistic Methods	5	III-IV/1st year
CS-E4600	Algorithmic Methods of Data Mining	5	I/1st year
CS-E4830	Kernel Methods in Machine Learning	5	I/2nd year
CS-E4840	Information Visualization	5	IV/1st year
CS-E4870	Research Project in Machine Learning and Data Science	5	I-II/2nd year

Major optional courses (choose 10-20 credits)

CODE	NAME	CREDITS	PERIOD/YEAR
CS-E4850	Computer Vision	5	III-IV/1st year
ELEC-E5510	Speech Recognition	5	II/2nd year
ELEC-E5550	Statistical Natural Language Processing	5	III-IV/1st year
CS-E5870	High-Throughput Bioinformatics	5	II/2nd year
CS-E4800	Artificial Intelligence	5	III-IV/1st year
CS-E4003	Special Assignment in Computer Science	1-10	I-V
CS-E4010	Special Course in Machine Learning and Data Science	3-10	I-V
CS-E4860	Special Course in Bioinformatics: Machine Learning in Bioinformatics	3-10	IV-V
CS-E5890	Statistical Genetics and Personalized Medicine	5	IV

Also other optional courses may be included per agreement with a professor in charge of the major.