Course content

The course is open for the students who are interested in artificial intelligence (AI) and willing to apply AI to practical applications. Focus will be on principles and implementation of AI methods for marine engineering. Throughout the course, students will gain the knowledge of concept, methodology and experiments from examples of real projects in marine domain. The course content are as follows:

• AI introduction
• Data collection, analysis and purification
• AI and control methods
  • supervised learning
  • unsupervised learning
  • reinforcement learning
  • deep learning…
• AI in different applications
  • Ship motion prediction
  • Engine fault diagnosis and prognosis
  • ANN-based controller for ship docking
  • Thruster fault detection and isolation
  • Deep reinforcement learning for COLREgs-compliant maneuvering
  • Sea state estimation…

Learning outcome

The students are expected to:

• Have a good understanding of AI methods and their pros and cons;
• Have knowledge of challenges in marine applications;
• Know how to deal with data, formulate the problem, simplify model complicity, and select AI methods;
• Be able to design and implement their own AI algorithms for real applications.

Learning methods and activities

Lectures, exercises and examples from real applications will be provided in the course. There will be individual mandatory assignments and exam project. 75% of the mandatory assignments have to be approved before admission to examination.

Compulsory assignments

• Individual Mandatory Assignments

Specific conditions

Recommended previous knowledge

The students are suggested to have the basic knowledge of linear algebra, statistics and some programming experience.

Required previous knowledge

None.

Course materials

• Jackson, Philip C. Introduction to artificial intelligence. Courier Dover Publications, 2019.
• Bishop, Christopher M. Pattern recognition and machine learning. springer, 2006.
• Sutton, Richard S., Barto, Andrew G. Reinforcement learning: An introduction. MIT press, 2018.
• A Beginner's Guide to Deep Reinforcement Learning, https://pathmind.com/wiki/deep-reinforcement-learning