Skip to main content

Deep LearningLaajuus (5 cr)

Code: R504D80

Credits

5 op

Objective

The students knows the fundamental concepts of deep learning, including various neural networks for supervised and unsupervised learning. The student can use some popular deep learning libraries applied in real industry problems.

Content

- Linear and non-linear regression, classification
- Foundations of neural networks and deep learning
- Techniques to improve neural networks: regularization and optimizations, hyper-parameter tuning and deep learning frameworks
- Applying deep learning to real-world scenarios such as object recognition and computer vision, image and video processing, text analytics and natural language processing,

Assessment criteria, satisfactory (1)

The student is familiar with neural networks and related machine learning methods.

Assessment criteria, good (3)

The student is familiar with neural networks and related machine learning methods. The student knows how to apply common deep learning frameworks.

Assessment criteria, excellent (5)

The student can explain and apply their knowledge of neural networks and related machine learning methods. The student knows how to apply feasible deep learning frameworks for a variety of deep learning applications.

Enrollment

18.03.2024 - 01.09.2024

Timing

02.09.2024 - 18.12.2024

Credits

5 op

Mode of delivery

Contact teaching

Unit

Bachelor of Engineering, Information Technology

Teaching languages
  • English
Seats

0 - 30

Teachers
  • Tuomas Valtanen
Responsible person

Tuomas Valtanen

Student groups
  • R54D22S

Objective

The students knows the fundamental concepts of deep learning, including various neural networks for supervised and unsupervised learning. The student can use some popular deep learning libraries applied in real industry problems.

Content

- Linear and non-linear regression, classification
- Foundations of neural networks and deep learning
- Techniques to improve neural networks: regularization and optimizations, hyper-parameter tuning and deep learning frameworks
- Applying deep learning to real-world scenarios such as object recognition and computer vision, image and video processing, text analytics and natural language processing,

Location and time

Lapland University of Applied Sciences, Rantavitikka Campus, 2.9.2024 - 13.12.2024

Materials

Lecture materials and exercises will be placed in the Moodle workspace.

Teaching methods

Lectures, workshops, examples, exercises and self-supervised work.

Exam schedules

The course will be graded based on personal work and exercise projects.

Content scheduling

- Foundations and theory of neural networks and deep learning
- Working on various types of data and use cases with various neural networks (ANN, MLP, CNN, RNN etc.)
- Techniques to improve neural networks: regularization and optimizations, hyper-parameter tuning and deep learning frameworks
+ other relevant topics

Evaluation scale

H-5

Assessment criteria, satisfactory (1)

The student is familiar with neural networks and related machine learning methods.

Assessment criteria, good (3)

The student is familiar with neural networks and related machine learning methods. The student knows how to apply common deep learning frameworks.

Assessment criteria, excellent (5)

The student can explain and apply their knowledge of neural networks and related machine learning methods. The student knows how to apply feasible deep learning frameworks for a variety of deep learning applications.

Assessment methods and criteria

The course will be graded on the scale of 1 - 5 and failed (0). The grading will be based on the submitted exercises/assignments.

Enrollment

02.10.2023 - 04.02.2024

Timing

05.02.2024 - 31.05.2024

Credits

5 op

Mode of delivery

Contact teaching

Unit

Bachelor of Engineering, Information Technology

Teaching languages
  • English
  • Finnish
Seats

0 - 30

Teachers
  • Tuomas Valtanen
Responsible person

Tuomas Valtanen

Student groups
  • R54D21S
    Bachelor of Engineering, Machine Learning and Data Engineering (full time studies), 2021

Objective

The students knows the fundamental concepts of deep learning, including various neural networks for supervised and unsupervised learning. The student can use some popular deep learning libraries applied in real industry problems.

Content

- Linear and non-linear regression, classification
- Foundations of neural networks and deep learning
- Techniques to improve neural networks: regularization and optimizations, hyper-parameter tuning and deep learning frameworks
- Applying deep learning to real-world scenarios such as object recognition and computer vision, image and video processing, text analytics and natural language processing,

Location and time

Lapland University of Applied Sciences, Rantavitikka Campus, 8.1.2024 - 15.5.2024

Materials

Lecture materials and exercises will be placed in the Moodle workspace.

Teaching methods

Lectures, workshops, examples, exercises and self-supervised work.

Exam schedules

The course will be graded based on personal work and exercises.

Content scheduling

- Linear and non-linear regression, classification
- Foundations of neural networks and deep learning
- Working on various types of data and use cases with neural networks
- Techniques to improve neural networks: regularization and optimizations, hyper-parameter tuning and deep learning frameworks
+ other relevant topics

Evaluation scale

H-5

Assessment criteria, satisfactory (1)

The student is familiar with neural networks and related machine learning methods.

Assessment criteria, good (3)

The student is familiar with neural networks and related machine learning methods. The student knows how to apply common deep learning frameworks.

Assessment criteria, excellent (5)

The student can explain and apply their knowledge of neural networks and related machine learning methods. The student knows how to apply feasible deep learning frameworks for a variety of deep learning applications.

Assessment methods and criteria

The course will be graded on the scale of 1 - 5 and failed (0). The grading will be based on the submitted exercises/assignments.