Deep Learning (5 cr)

Evaluation scale

H-5

Content scheduling

Course Overview:

This course explores the fundamental principles of deep learning and neural networks, diving into architectures like CNNs, RNNs. Students will gain hands-on experience building models using modern DL libraries and apply them to real-world problems in vision, sequence modeling, and more.

- Week 37: Introductionary session => 3 hours
- Week 38-48: weekly 10 times 3h (30h) Theory and practice
- Week 49: Final Project Demonstration or Exam (3h)
- In addition, about 4 support and inquiry online hours (biweekly): 4x 1h = 4h

Objective

After completing the course, the student can:
- Can define the main concepts, values and drivers for deep learning
- Can describe how machine learning and AI solutions can be developed with deep learning and neural networks
- Use tools when creating the solutions

Content

Deep Learning
Neural Networks
Natural Language Processing
Pattern Recognition
Computer Vision
Practical work

Materials

Course materials are prepared by the lecturers from various sources including books, online material, etc.

Recommended books to study in this course are:
-- Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems 3rd Edition by Aurélien Géron, OREILLY, 2023

Teaching methods

- Weekly contact lessons:
- Theory
- Practice

- Biweekly extra online Q&A sessions

Exam schedules

Exam will be in week 49 (at the same date as we have the regular lectures).
Note: minimum 50% of exam points is required to pass

Retake in May 2026

Pedagogic approaches and sustainable development

- The course includes approximately 12 theory and practice sessions, where students engage with practical tasks.
- Additionally, there are 4 online Q&A sessions to provide extra support.
- Homework exercises will be assigned, with some parts demonstrated during contact sessions.
- An exam will be taken at the final session.

Sustainability is integrated in the implementation topics.

Completion alternatives

The exercises are mainly performed using Jupyter Notebook. Student will use TensorFlow or PyTorch. Strong python programming is need to complete the exercises.

Student workload

- Week 37: Introductionary session => 3 hours
- Week 38-48: weekly 10 times 3h (30h) Theory and practice
- Week 49: Final Project Demonstration or Exam (3h)
- In addition, about 4 support and inquiry online hours (biweekly): 4x 1h = 4h

- Total contact teaching: 40h
- Independent study and homework: about 95h

- Total workload: 135h

Evaluation methods and criteria

You can achieve points from lesson participation, exercises (homework or classwork), and exam.

Lesson participation (effect 20%):
- Full points if student participates over 70% of the lectures.
- Half points if student participates 50% of the lectures.
- Zero points if student participate lesser than 50% of the lectures

Exercises (effect 40%):
- Full points from the achieved points if students submit the exercise on time
- Half points from the achieved points if students submit the exercise after deadline

- Exam (effect 40%)

Note: Minimum 50% of final project or exam points and exercises points points are required to pass the course!

The course is graded on a scale of 0-5.
Grading will be according to the total points collected by the student during the course as well as the exam.
1: 50% (minimum to pass the course)
2: 60-69%
3: 70-79%
4: 80-89%
5: 90- 100%

Failed (0)

Less than 50% in assignments not passed.

Assessment criteria, satisfactory (1-2)

1: 50% - 59% from the total points of the assignments

2: 60% - 69% from the total points of the assignments

Assessment criteria, good (3-4)

3: 70% - 79% from the total points of the assignments

4: 80% - 89% from the total points of the assignments

Assessment criteria, excellent (5)

90%- 100% from the total points of the assignments

Further information

Qualifications:
Before taking a "Deep Learning" course, students typically need a foundational understanding of several key areas. Here are the mandatory and recommended prerequisite courses and topics.

1. Mandatory Prerequisites:
1.1. Programming:
1.1.1. Introduction to Programming: Knowledge of programming fundamentals,
including concepts like variables, loops, conditionals, and functions.
1.1.2. Python Programming: Familiarity with Python, including basic syntax, data
types, control structures, and function and modules, libraries like Pandas, Numpy, Scikit-learn, and Matplotlib,
1.2 Data Analytics and Machine Learning

2. Recommended Topics:
2.1. Algorithms and Data Structures: Basic understanding of algorithms and data
structures such as arrays, lists, trees, and graphs, which are crucial for data
processing
2.3. Version Control Systems: Basic understanding of tools like Git for version control.
2.4. Basic Algebra and Calculus: Fundamental math skills to handle data transformations
and calculations.
2.5. Statistics: Understanding of basic statistical concepts like mean, median, standard
deviation, and probability distributions.

Note!
Use of Artificial Intelligence (AI) in Exams and Exercises: Restricted
-The use of Artificial Intelligence (AI), particularly generative AI tools, is prohibited in all exams and exercises unless explicitly authorized for a particular task.

Student's Own Work:
-All submitted output for exams and exercises must be created without prohibited AI assistance.
-Students should use only their own knowledge, understanding, and skills.

Prohibition of Unauthorized AI:
The use of AI (including but not limited to text generators, image creators, or code assistants) is forbidden for completing coursework unless the instructor has expressly granted permission for its use on a specific assignment, outlining acceptable parameters.

Justification for Restriction:
-This policy is in place to ensure that students develop and demonstrate their own skills and understanding, and to maintain academic integrity.

Interpretation as Fraud:
-Any use of AI that has not been explicitly allowed will be interpreted as fraud and addressed according to the institution's academic misconduct policies.