Course - Machine Learning for Engineers - TMM4128
Machine Learning for Engineers
Assessments and mandatory activities may be changed until September 20th.
About
About the course
Course content
Machine learning (ML) is a branch of AI that focuses on learning from data to design automated systems that can improve their performance with experience. In recent years, machine learning has been used in a wide range of engineering applications, including: autonomous cars, predicting mechanical failure, quality assessment, automation of engineering tasks, robotic vision and intelligent control among others.
This course provides a thorough introduction to machine learning and hands-on experience with its practical applications. The topics taught in this course will cover fundamental principles in machine learning as well as the theoretical bases for its algorithms and how they can be optimally applied.
The focus is made on adaptation, combination and application of existing ML tools for solving engineering problems considering product development lifecycle, including product development, manufacturing, use and potential recycle/reuse/repurpose. At the end one should be able i) to identify suitable ML-based approaches for solving an engineering problem, ii) find right components, tools to implement the approach and iii) integrate and fine-tune those components to develop the solution.
Learning outcome
Having successfully completed this course student will be able to acquire the following:
Knowledge:
- Learn the fundamental principles of supervised, unsupervised and reinforcement learning.
- Acquiring knowledge of using and finetuning ML to solve practical problems relevant for engineers.
Skills:
- Apply data handling, feature engineering and data pre-processing techniques
- Gain experience to systematically work with data to learn new patterns.
General competence:
- At the end of this course students will understand the strengths and limitations of well-known machine learning methods, and learn how to analyse data to identify trends.
Learning methods and activities
Learning activities in this course include: lectures, preparing seminars, working on mini projects, and contribution to discussion.
The examination papers will be given in English only. It is also expected that English is used for answering the exam.
Compulsory assignments
- Group Presentations
Further on evaluation
Portfolio assessment and final exam are the bases of the course grade. The grade is divided into 40% for portfolio assessment and 60% for final exams.
The portfolio includes 3 assignments each focusing the application of a machine learning model. It revolves around choosing a data set and applying machine learning models in real world applications.
The seminars will include a short seminar that introduces the chosen data set for the project and a longer seminar that explains the pace of work after the project midterm report has been submitted.
In these three presentations students are expected to participate.
The project can be carried out in a group of 2-3 students and it should include a detailed description of the individual contribution of the participants.
In addition, there will be compulsory oral presentations of 3 course assignments used as a pedagogical tool to disseminate knowledge gathered by groups of students among each other.
If there is a re-sit examination, the examination form may be changed from written to oral.
Recommended previous knowledge
A good background in linear algebra (matrices and eigenvector), calculus, probability, as well as programming skills in python or MATLAB. Also, taking TPK4186 - Advanced Tools for Performance Engineering or similar courses in the third year would be useful.
Course materials
Textbooks:
- Tom Mitchell: Machine learning, McGraw Hill, 1997
- Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006
Additional course materials (textbook and papers) will be provided in the lectures.
Subject areas
- Machine Design and Materials Technology - Materials Production Processes
- Machine Design and Materials Technology - Mechanical Integrity
- Machine Design and Matherials Technology - Products and Machine Design
- Computer and Information Science
- ICT and Mathematics
- Machine Design and Materials Technology
- Computers
- Machine Design and Materials Technology - Mechanical Integrity in Machine Design
- Computer Systems
- Computer Systems