Signal Processing and Machine Learning, 30 cr
Type of the study module
Intermediate Studies
Contact
Sari Peltonen, Joni Kämäräinen, Heikki Huttunen
Learning Outcomes
- | Opiskelija osaa soveltaa koneoppimis- ja signaalinkäsittelymenetelmiä tietotekniikassa.
Student knows how to adopt and adapt signal processing and machine learning methods for real problems. Opiskelija kykenee löytämään kehittyneitä menetelmiä kirjallisuudesta sekä muokkaamaan niitä käsillä olevaan ongelmaan sopivaksi. Student is able to find state-of-the-art methods and adapt them to to solve practical problems. Opiskelija osaa käyttää Matlab/Python-kirjastoja koneoppimis- ja signaalinkäsittelyongelmien laskennalliseen ratkaisemiseen. The student can use Matlab/Python libraries to solve machine learning and signal processing problems. Opiskelija osaa soveltaa koneoppimista ja älykkäitä menetelmiä audion, kuvan ja robotiikan sovellusalueilla. The student can apply pattern recognition, machine learning and signal processing method in audio, vision and robotics. |
Prerequisites
Passing the module requires programming skills and understanding of the engineering mathematics. ( Advisable )
Opintojakso SGN-11000 Signaalinkäsittelyn perusteet on pakollinen esitieto. Jos opintojakso SGN-11000 Signaalinkäsittelyn perusteet ei kuulu opiskelijan pakollisiin perusopintoihin, sisällytetään se tähän moduuliin. Tällöin opiskelija voi halutessaan suorittaa vain toisen opintojaksoista SGN-14007 Introduction to Audio Processing ja SGN-12001 Johdatus kuvan- ja videonkäsittelyyn.
The course SGN-11007 Introduction to Signal Processing is a mandatory prerequisite. If the course SGN-11007 Introduction to signal processing is not part of mandatory basic studies, the student may include it into this module. In this case, it is allowed to take only one of the courses SGN-14007 Introduction to Audio Processing ja SGN-12007 Introduction to Image and Video Processing.
Courses SGN-11000 and SGN-11007 share the same contents and student should take only one of them. ( Mandatory )
Further Opportunities
Study block | Credit points |
Robotics | 30 cr |
Signal Processing and Machine Learning | 30 cr |
Content
Compulsory courses
Course | Credit points | Additional information | Class |
SGN-12001 Johdatus kuvan- ja videonkäsittelyyn | 5 cr | 1 | III |
SGN-12007 Introduction to Image and Video Processing | 5 cr | 1 | III |
SGN-13006 Introduction to Pattern Recognition and Machine Learning | 5 cr | III | |
SGN-14007 Introduction to Audio Processing | 5 cr | III | |
Total | 20 cr |
1. Select only one of the two alternative courses
Optional Compulsory Courses
SGN-80000 Signaalinkäsittelyn kandidaattiseminaari on pakollinen, mikäli kokonaisuuteen tehdään kandidaatintyö. SGN-80000 is compulsory to students who do this module as major in their B.Sc. degree.
Course | Credit points | Class |
SGN-80000 Signaalinkäsittelyn kandidaattiseminaari | 0 cr | III |
Complementary Courses
Kokonaisuus voidaan suorittaa sivuaineena suorittamalla moduulin pakolliset kurssit ja valinnaisia niin, että laajuudeksi tulee 20 op. Pääaineena laajuus on 30 op. Note that for several of the courses there are Finnish/English alternatives in which case either (but only one) is accepted. Note also that the list is not exhaustive and students may propose suitable alternative courses to substitute those in the list (discuss with the major responsible persons). Students are specially encouraged to search for suitable complementary courses and agree them with the study module responsible teachers.
Should be completed to the minimum study module extent of 30 ETCS
Course | Credit points | Class |
ASE-1259 Introduction to Control | 5-7 cr | III |
ASE-2110 Systeemit ja säätö | 5 cr | III |
ASE-2117 Systems and Control | 5-7 cr | III |
IHA-4306 Fundamentals of Mobile Robots | 5 cr | |
MAT-02510 Tilastomatematiikan jatkokurssi | 5 cr | III |
SGN-45007 Computer Vision | 5 cr | |
TIE-20106 Data Structures and Algorithms | 5 cr | III |
TIE-22307 Data-Intensive Programming | 5 cr | III |
Additional information
Signal processing and machine learning are central fields in the modern information technology and computer science. Emerging applications are vast varying from visual (computer vision), speech and audio recognition to autonomous robots and cars. A related field is data engineering which means machine learning algorithms applied to large datasets from finance, security, health, biology, Internet and so on. This module provides students strong practical knowledge and expertise on the main approaches and methodologies of machine learning and pattern recognition. Moreover, the students will have hands-on experience on the most emerging applications of these: computer vision, audio and speech processing and data engineering.
It is also possible to take the module as a minor with 20 credits worth of courses (the mandatory ones in the list).
The students are encouraged to contact the responsible persons of this study module to personalize and tailor their studies.