Study Guide

Objective

Students will be competent in using the mathematical methods described in the course contents to solve practical mathematical problems.

Content

Basics of machine learning:
Minimization by gradient descent
Linear regression
Logistic regression
Neural networks

Materials

Lecture material and demonstrations

Teaching methods

Lectures, exercises

Student workload

81h

Further information

80% attendance in lectures and exercises

Evaluation scale

1-5

Assessment criteria, satisfactory (1)

satisfactory (1-2): The student knows and understands to a satisfactory extent the basic concepts and methods discussed in the course, and is able to apply them to usual problems.

Assessment criteria, good (3)

good (3-4): The student is familiar with the concepts and methods discussed in the course, and is able to apply them to different types of problems. The student is able to combine the accumulated knowledge and skills with previous experiences in the subject.

Assessment criteria, excellent (5)

excellent (5): The student is familiar with the concepts and methods discussed in the course, and is able to apply them to a variety of different problems. The student has demonstrated creativity and innovation, and is able to find new meanings when applying what they have learned

Assessment methods and criteria

assignments

Qualifications

Algebra and geometry, Vectors and matrices, Differential and integral calculus, Automation technology mathematics