Emner innen kunstig intelligens og maskinlæring

This course covers topics in artificial intelligence and machine learning, both theory and practice, recent research papers and state-of-the-art techniques.

The main topics are:

• Artificial Neural Networks and Deep Learning
• Soft Computing by Fuzzy Systems
• Machine Learning: Supervised Learning, Unsupervised Learning and Reinforcement Learning
• Other Concepts and Methods in AI, including evolutionary computing and complex systems (complex networks, cellular automata, and agent-based models).

The course will be offered once a year, provided 3 or more students sign up for the course. If less than 3 students sign up for a course, the course will be cancelled for that year.

Basic knowledge in calculus, linear algebra, statistics, and probability theory. Knowledge of a programming language (especially Python).

None.

Students who complete the course are expected to have the following learning outcomes, defined in terms of knowledge, skills and general competence:

Knowledge

On successful completion of the course, the student has:

• an in-depth understanding of machine learning methods: supervised, unsupervised, and reinforcement learning, both theoretical and applied, to solve real-world problems.
• knowledge and understanding of the main concepts of artificial neural networks and deep learning.
• knowledge and understanding of some key concepts in artificial intelligence, including: soft computing (fuzzy systems), evolutionary computing, and complex systems (complex networks, cellular automata, and agent-based models).

Skills

On successful completion of the course, the student can:

• apply techniques from AI and machine learning to real-world problems.
• analyze data with AI and machine learning algorithms.

General competence

On successful completion of the course, the student can:

• use libraries (such as PyTorch and TensorFlow) for programming machine learning and deep learning algorithms.
• deploy models to real-world problems.
• solve search or optimization problems using evolutionary algorithms.

Each module will be taught in a series of lectures. The students will be assigned a small project to be submitted within a given deadline.

The following required coursework must be approved before the student can take the exam:

Mandatory assignment(s) must be approved prior to the exam. The students must submit the report (with code) for a small project.

Oral exam, individual.

The exam cannot be appealed.

None.

Pass or fail.

Two internal examiners. External examiner is used periodically.

Jianhua Zhang