DSP713 Machine learning

Code DSP713
Name Machine learning
Status Compulsory/Courses of Limited Choice
Level and type Post-graduate Studies, Academic
Field of study Computer Science
Faculty
Academic staff Agris Ņikitenko
Credit points 3.0 (4.5 ECTS)
Parts 1
Annotation The study course addresses the question of how to enable computers to learn from past experiences. The main theories of artificial intelligence, statistics, information, etc. are discussed. terms and techniques to the extent applicable to machine learning..
Contents
Content Full- and part-time intramural studies Part time extramural studies
Contact hours Independent work Contact hours Independent work
Introduction - learning paradigms. 4 0 0 0
Concept learning. 4 0 0 0
Clusterization. 6 10 0 0
Decision trees. 6 10 0 0
Artificial neural networks. 12 10 0 0
Genetic algorithms. 12 10 0 0
Text analysis. 8 10 0 0
Time series analysis and classification. 8 10 0 0
Total: 60 60 0 0
Goals and objectives
of the course in terms
of competences and skills
The aim of the study course is to provide knowledge of the most important algorithms and theories that form the basis of machine learning, as well as to provide appropriate practical skills. Tasks of the study course are to provide knowledge and skills: - to apply the machine learning techniques covered in the course using Python or an equivalent programming language; - to apply software tools and libraries appropriate to the methods; - to be able to identify the appropriate method and tool for a specific problem; - to be able to debug the code implementing the method, as well as to adjust the hyperparameters of specific methods; - to be able to interpret the obtained results and make decisions on the compliance of the applied method and hyperparameter values with the expected result.
Learning outcomes
and assessment
Is able to describe the main principles, advantages and limitations of machine learning. - Appropriate questions in the exam.
Is able to apply and finetune clusterization. - Appropriate questions in the exam. Individual practical work.
Is able to apply and finetune classification methods. - Appropriate questions in the exam. Individual practical work.
Is able to apply and finetune artificial neural networks. - Appropriate questions in the exam. Individual practical work.
Is able to apply and finetune text analysis algorithms. - Appropriate questions in the exam. Individual practical work.
Is able to apply and finetune genetic optimization methods. - Appropriate questions in the exam. Individual practical work.
Is ably to apply time series analysis and classification methods. - Appropriate questions in the exam. Individual practical work.
Evaluation criteria of study results
Individual practical work - 50%
Exam - 50%
 
Course prerequisites Mathematics, probability theory.
Course planning
Part CP ECTS Hours Tests
Lectures Practical Lab. Test Exam Work
1 3.0 4.5 2.0 1.0 0.0 *

[Extended course information PDF]