FMG3100 Basic Applications of Neural Networks in Manufacturing 1.5 credits

Engineering is experiencing a drastic change due to the ubiquitous presence of computers and internet. This fact has triggered the designation of this phenomenon as the fourth industrial revolution, and the application of the associated term Industry 4.0. One of the important components envisioned in the Industry 4.0 is artificial intelligence. It is a field within computer science that has achieved a stepwise progress in the last half a century. The last of these steps is associated with Deep learning. It is a field within machine learning that relies on artificial neural networks with multiple layers. The course aims at giving the basic understanding of an artificial neural network operation and enabling students to use the more complex neural networks for their research. The activities are tailored for PhD students in the domain of manufacturing.

After successful completion of this course, the students will be able to:

• Based on a case study proposed by the course leader, program a very basic neural network from scratch in Python
• Contextualize and use more complex neural networks with the help of Neurolab and Keras libraries
• Discuss and describe basic application of machine vision

PhD student

Basic knowledge of programming in any computer language, but Python is the preferred choice. The students should have some familiarity with the basic concepts of multivariate analysis and linear algebra (mainly matrix manipulation).

The course is based on hand-outs from the course leader that will be provided along the course

If the course is discontinued, students may request to be examined during the following two academic years.

• PRO1 - Project, 1.5 credits, grading scale: P, F

Based on recommendation from KTH’s coordinator for disabilities, the examiner will decide how to adapt an examination for students with documented disability.

The examiner may apply another examination format when re-examining individual students.

The assessment of students’ work will be based mainly on the project report. If deemed appropriate students will be encouraged to publish a journal paper (with the help of the supervisors).

Antonio Maffei

• All members of a group are responsible for the group's work.
• In any assessment, every student shall honestly disclose any help received and sources used.
• In an oral assessment, every student shall be able to present and answer questions about the entire assignment and solution.