Introduction to artificial intelligenceLaajuus (5 cr)
Code: YT00CF50
Credits
5 op
Responsible person
- Matti Welin
- Rami Viksilä
- Minna Asplund
Objective
The student is able to
- identify the key features of neural networks and deep learning
- study hyperparameters, activation functions, and neural network topology
- handle hidden layers as well as predict using existing data
- take into account usage of resources and the ethical aspects of artificial intelligence
Enrollment
06.05.2024 - 30.08.2024
Timing
04.11.2024 - 07.11.2024
Number of ECTS credits allocated
5 op
Virtual portion
5 op
Mode of delivery
Distance learning
Unit
Faculty of Technology (LAB)
Campus
E-campus, Lahti
Teaching languages
- Finnish
Seats
5 - 40
Degree programmes
- Master’s Degree Programme in Engineering, from IoT to AI (in Finnish)
Teachers
- Matti Welin
- Minna Asplund
- Rami Viksilä
Scheduling groups
- Luennot 1 (Size: 100. Open UAS: 0.)
Groups
-
TLTIYITT24KV
Small groups
- Lecture 1
Learning outcomes
The student is able to
- identify the key features of neural networks and deep learning
- study hyperparameters, activation functions, and neural network topology
- handle hidden layers as well as predict using existing data
- take into account usage of resources and the ethical aspects of artificial intelligence
Assessment scale
1-5
Enrollment
20.11.2023 - 05.01.2024
Timing
11.03.2024 - 14.03.2024
Number of ECTS credits allocated
5 op
Virtual portion
5 op
Mode of delivery
Distance learning
Unit
Faculty of Technology (LAB)
Campus
E-campus, Lahti
Teaching languages
- Finnish
Seats
5 - 40
Degree programmes
- Master’s Degree Programme in Engineering, from IoT to AI (in Finnish)
Teachers
- Matti Welin
- Minna Asplund
- Rami Viksilä
Scheduling groups
- Verkkoluento 1 (Size: 500. Open UAS: 0.)
Groups
-
TLTIYITT23SV
Small groups
- Online lecture 1
Learning outcomes
The student is able to
- identify the key features of neural networks and deep learning
- study hyperparameters, activation functions, and neural network topology
- handle hidden layers as well as predict using existing data
- take into account usage of resources and the ethical aspects of artificial intelligence
Assessment scale
1-5
Enrollment
21.11.2022 - 08.01.2023
Timing
27.02.2023 - 06.04.2023
Number of ECTS credits allocated
5 op
Virtual portion
5 op
Mode of delivery
Distance learning
Unit
Faculty of Technology (LAB)
Campus
E-campus, Lahti
Teaching languages
- Finnish
Seats
5 - 30
Degree programmes
- Master’s Degree Programme in Engineering, from IoT to AI (in Finnish)
Teachers
- Matti Welin
- Minna Asplund
- Rami Viksilä
Scheduling groups
- Luennot 1 (Size: 500. Open UAS: 0.)
Groups
-
TLTIYITT22SV
Small groups
- Luennot 1
Learning outcomes
The student is able to
- identify the key features of neural networks and deep learning
- study hyperparameters, activation functions, and neural network topology
- handle hidden layers as well as predict using existing data
- take into account usage of resources and the ethical aspects of artificial intelligence
Assessment scale
1-5
Enrollment
19.11.2021 - 09.01.2022
Timing
14.03.2022 - 17.03.2022
Number of ECTS credits allocated
5 op
Virtual portion
5 op
Mode of delivery
Distance learning
Unit
Faculty of Technology (LAB)
Campus
E-campus
Teaching languages
- Finnish
Seats
10 - 40
Degree programmes
- Master’s Degree Programme in Engineering, from IoT to AI (in Finnish)
Teachers
- Matti Welin
- Minna Asplund
- Juhani Grape
- Rami Viksilä
Scheduling groups
- Opetus (Size: 0. Open UAS: 0.)
Groups
-
TLTIYITT21S
Small groups
- Lectures
Learning outcomes
The student is able to
- identify the key features of neural networks and deep learning
- study hyperparameters, activation functions, and neural network topology
- handle hidden layers as well as predict using existing data
- take into account usage of resources and the ethical aspects of artificial intelligence
Assessment scale
1-5