Skip to main content

Basics of Machine Learning and Classification in Python (3cr)

Code: 5G00FC54-3001

General information


Enrolment period
27.05.2019 - 30.09.2019
Registration for the implementation has ended.
Timing
26.08.2019 - 22.12.2019
Implementation has ended.
Credits
3 cr
RDI portion
2 cr
Mode of delivery
Contact learning
Campus
TAMK Main Campus
Teaching languages
Finnish
Degree programmes
Degree Programme in ICT Engineering, students who began in 2014-2018
Teachers
Mauri Inha
Hanna Kinnari-Korpela
Person in charge
Hanna Kinnari-Korpela
Course
5G00FC54

Objectives (course unit)

The aim is to provide a tool package ("a set of algorithms") to be able to solve simple real world problems with machine learning.

The course time load will averagely be: 20 % in-class lectures and 80 % of student own/pair working.

Content (course unit)

Timetable:
Lecture 1. 9.10. Introduction. Basic of machine learning and classification. Introducing the course assignments. Homework.

16.10. Autumn brake

Lecture 2. 30.10. Decision Trees and Random Forests. Homework.

Lecture 3. 13.11. Support Vector Machines. Homework.

Lecture 4. 27.11. Ensemble Learning, Bagging and Boosting. Homework

Lecure 5. 11.12. Exam.

Prerequisites (course unit)

Knowledge and skills of basics of programming and engineering mathematics.

Assessment criteria, satisfactory (1-2) (course unit)

Evaluation/grading criteria:
40 % from course exercises
40 % from course assignment
20 % from multiple choice exam

A student with the best course assignment will get the final grade + 1.

The student must complete at least one course exercise. Grades from course exercises:
1 working exercise = grade 2
2 working exercise = grade 3
3 working exercise = grade 4
4 working exercise = grade 5

Assessment criteria, good (3-4) (course unit)

Evaluation/grading criteria:
40 % from course exercises
40 % from course assignment
20 % from multiple choice exam

A student with the best course assignment will get the final grade + 1.

The student must complete at least one course exercise. Grades from course exercises:
1 working exercise = grade 2
2 working exercise = grade 3
3 working exercise = grade 4
4 working exercise = grade 5

Assessment criteria, excellent (5) (course unit)

Evaluation/grading criteria:
40 % from course exercises
40 % from course assignment
20 % from multiple choice exam

A student with the best course assignment will get the final grade + 1.

The student must complete at least one course exercise. Grades from course exercises:
1 working exercise = grade 2
2 working exercise = grade 3
3 working exercise = grade 4
4 working exercise = grade 5

Location and time

Ensimmäinen kerta 9.10.2019 !!!!!
16.10 on syysloma.

Assessment scale

0-5

Go back to top of page