KIUA1006 Machine Learning II
- Course codeKIUA1006
- Number of credits10
- Teaching semester2025 Autumn
- Language of instructionNorwegian/English
- CampusHamar
- Required prerequisite knowledge
Recommended: KIUA1001 Machine Learning I, KIUA1006 Programming II and KIUA1004 Probability and Statistics
The course provides fundamental knowledge and skills in advanced machine learning. Students will gain an understanding of advanced machine learning concepts and theories, deep learning architectures and algorithms, natural language processing and computer vision techniques, as well as the ethical implications of machine learning. Students will also develop technical skills in computer science and frameworks for deep learning, as well as communication and problem-solving skills. Real-world examples of interactive simulation used in AI contexts, such as optimisation of supply chain logistics using AI, understanding of feedback loops in social media algorithms and the growth and proliferation of AI technologies will be provided.
Learning Outcome
Upon successfully passing the course, students will have achieved the following learning outcomes:
The student will have
- knowledge of the principles of deep learning architectures and algorithms such as convolutional neural networks (CNN), recurrent neural networks (RNN) and generative adversarial networks (GAN).
- general knowledge of natural language processing and computer vision techniques such as sentiment analysis, i.e. device recognition, image segmentation and facial recognition
- knowledge of the ethical implications of machine learning, such as bias, fairness, privacy and security
- knowledge of feedback loops, inventories and flows, delays and how these components can be used to model real-world systems
The student will be able to
- pre-process and prepare data for machine learning, including data cleansing, missing value management, feature selection and dimensionality reduction by applying data normalisation and scaling techniques
- implement machine learning models using suitable programming languages and libraries and be able to evaluate model performance, adjust hyperparameters and select appropriate models for different tasks
- interpret and communicate machine learning results to analyse model results, visualise data and efficiently communicate insights and findings to both technical and non-technical stakeholders
- identify real-world problems that can be solved using machine learning methods from a system perspective
- use CLDs to describe the feedback loops in recurring neural networks (RNN, CNN and GAN)
The student will be able to
- analyse, manipulate and interpret complex data using machine learning technologies such as CNNs, RNNs and GANs
- develop and implement machine learning models for real-world applications using fundamental deep learning frameworks
- promote a mindset of continual learning and adaptability in machine learning to recognise the dynamic nature of the field and to be prepared to update their knowledge and skills in line with new technologies and algorithms becoming available
- communicate ideas and contribute to collective problem-solving in machine learning projects through group projects and assignments
The course comprises a combination of lectures, practical exercises, independent study and academic supervision.
| Form of assessment | Grading scale | Grouping | Duration of assessment | Support materials | Proportion | Comment |
|---|---|---|---|---|---|---|
Written assignment | ECTS - A-F | Group | 100 |
- One project-based group assignment
The assignment is assessed using a grading scale from A-F, where E is the lowest passing grade.
Students are able to choose which language to use for their examination. The available options are Norwegian Bokmål, Nynorsk and English.
Permitted aids:
- Literature
- All printed and written resources
- Any use of AI-generated text and content must be clarified with the lecturer, clearly labelled and academically justified in the submission