Study Guide

Objectives (course unit)

After completing the course, the students will be able to:
- Select approprite ML/AI algorithm for common use cases
- Use trained model to make classifications or predictions
- Train new ML/AI models with prepared data

Content (course unit)

Basic concepts and different types of Machine Learning and AI, Concepts and requirements with data preparation, Making predictions and classifications with pre-trained models in Python, Training custom models with own data in Python.

Prerequisites (course unit)

Basics of Programming with any language preferred. Pyhton language will be used in the course.

Assessment criteria, pass/fail (course unit)

The student is able to reach the objectives of this course
The student is not able to reach the objectives of this course

Location and time

Autumn 2022 (Fridays of the first and second periods). Starting: September 2, 2022 – see Moodle for details.

Exam schedules

No exam by default. Assessment based on working during the course (tests, exercises/assignments, presentations).

Assessment methods and criteria

Pass/fail grading applied. Passing the course (or not) determined based on the number of points gathered from the course activities (tentatively 50% required). Moreover, there may be mandatory activities/assignments that have to be passed in order to pass the course.

Assessment scale

0-5

Teaching methods

Remote teaching (see Moodle, probably some sessions also at TAMK premises), independent studying, problem-based learning, exercises/assignments, presentations, working independently and in groups

Learning materials

To be announced.

Student workload

Planned student workload approximately 135 hours, distributed evenly over the first and second periods.

Completion alternatives

n/a

Practical training and working life cooperation

n/a