This translation is for information purposes only. In the event of discrepancies, the Swedish-language version takes precedence.

Deep Learning for Automation, 4.5 Credits

Djupinlärning för automation, 4,5 Högskolepoäng

Established: 2023-03-01

Established by: Department of Engineering Science

Applies from: H23

Learning outcomes

After completing the course, the student should be able to:

Knowledge and understanding

• show understanding of the way artificial neural networks (ANN) and deep neural network (DNN) are trained
• discuss the workings of some of the modern ANN and DNN architectures, eg CNN, LSTM etc

Competence and skills

• select a suitable approach to solve a practical problem using ANN/DNN
• utilize existing libraries to build ANN/DNN applications
• design a relevant set of performance matrices in order to validate the performance of algorithms
• evaluate the performance of algorithms based on a relevant set of performance matrices
• utilize results from experiments to re-design and fine tune the ANN/DNN architectures to meet the requirements of the task

Judgement and approach

• relate to salient aspects of the EU AI Regulation

Entry requirements

General entry requirements and approved result from the following course/courses: PFA600-Programming for Automation and MFA600-Mechatronics for Automation and IAI600-Introduction to Artificial Intelligence and Machine Learning or the equivalent.

The forms of assessment of student performance

Individual written laboratory-work report. Written project report in group with oral presentation.

Course contents

The course introduces the modern algorithms around deep learning. Practical applications in automation are taken up and processed. The focus of the course is on the following areas:

• Introduction to artificial neural networks (ANN)
• Perceptron and back-propagation algorithm
• Deep learning network
• Some interesting DNN networks (eg CNN, LSTM etc.)
• Applications in some domains (eg computer vision, NLP etc.)
• Processing Sequence in Deep Learning
• Practical aspects of training and deploying a Deep Learning solution

Other regulations

Course grading: F/Fx/E/D/C/B/A - Insufficient, Insufficient- more work required before the credit can be awarded, Sufficient, Satisfactory, Good, Very Good, Excellent

Course language: The teaching is conducted in English.

General rules pertaining to examination at University West are available at www.hv.se.

If the student has a decision/recommendation on special support due to disability, the examiner has the right to examine the student in a customized examination form.

Cycle

Second cycle

Progressive specialization

A1F - Second cycle, has second-cycle course/s as entry requirements

Main field of study

Automation, Production Technology