Study Guide

Objective

After completing the course, the students can
- work in the AI project
- describe and understand how AI projects are implemented

Content

Practical project related to AI

Materials

The course materials will be announced later during the course.

Exam schedules

No Exam

Student workload

Contact hours:
- 4 times 4h theory and practice: 4 x 4h = 16 hours

Final project: approximately 114 hours

Total: approximately: 130 hours

Content scheduling

A deep learning-focused, project-based course that empowers master's students to explore and develop AI projects, fostering their ability to conceive, implement, and optimize intelligent solutions.

Session 1: AI Project Lifecycle and Data Selection
Session 2: Data Preprocessing and Model Selection
Session 3: Presenting First Results and Discussion
Session 4: Algorithm Optimization and Tuning

Further information

This course is project-based, requiring students to possess knowledge in machine learning and deep learning, specifically in image recognition and Sequential models.
Consequently, it is advisable to enroll in the 'Components and Applications of Artificial Intelligence' course first. In that course, students learn how to employ deep neural networks for image recognition (using CNN) and using RNN for sequential models. This foundational knowledge will better prepare students for the project-based nature of this course.

Evaluation scale

Hyväksytty/Hylätty