Neural Networks for Machine Learning Applications (5 ECTS)

Objective

The student
- understands the structure of various types of neural networks and the basic mathematical machinery behind their operation,
- acquires the knowledge needed to create neural networks and work with them; and skills related to programming, data manipulation, method selection, model building, and interpreting the outcome, and
- learns to apply these skills in different machine learning tasks involving e.g. image classification and natural language processing.

Content

Basics of artificial neural networks, convolutional and recurrent neural networks, applications of neural networks.

Evaluation scale

0-5

Assessment criteria, satisfactory (1)

Students have achieved the course objectives fairly. Students will be able to identify, define and use the course subject area’s concepts and models. The student understands the criteria and principles of the expertise development.

Assessment criteria, good (3)

Students have achieved the course objectives well, even though the knowledge and skills need improvement on some areas. Students are able to define the course concepts and models and are able to justify the analysis. The student is able to apply their knowledge in leisure, study and work situations. The student understands the importance of expertise in the field of information technology and is able to analyze his/her own expertise.

Assessment criteria, excellent (5)

Students have achieved the objectives of the course with excellent marks. Students master commendably the course subject area’s concepts and models. Students are able to make justified and fluent analysis and to present concrete development measures. The students are well prepared to apply their knowledge in leisure, study and work situations. Students are able to analyze the information technology sector expertise and the evolvement of their own expertise.

Assessment criteria, approved/failed

Students have achieved the course objectives. Students will be able to identify, define and use the course subject area’s concepts and models. The student understands the criteria and principles of the expertise development.

Qualifications

Basic algebra and statistics, intermediate programming skills, knowledge on handling measurement data.

Further information

The elective course “Mathematics and Methods in Machine Learning and Neural Networks” supports this course. It is recommended that the student participates both courses simultaneously.

Further information

The elective course “Mathematics and Methods in Machine Learning and Neural Networks” supports this course. It is recommended that the student participates both courses simultaneously.