Duration
20h Th, 20h Pr
Number of credits
| Master MSc. in Civil Engineering, professional focus in civil engineering | 3 crédits |
Lecturer
Language(s) of instruction
English language
Organisation and examination
Teaching in the first semester, review in January
Schedule
Units courses prerequisite and corequisite
Prerequisite or corequisite units are presented within each program
Learning unit contents
The focus of this class is on actionable understanding of how machine learning (ML) techniques can be leveraged to solve different types of problems. It is intended for students who do not necessarily have previous exposure to ML. The class covers all major algorithms related to regression and classification tasks in the supervised learning setting, including generalized linear models, various flavors of decision trees, and neural networks. The class will also cover strategies for effective training of ML models as well as how to structure machine learning projects. The key part of the learning experience will be implementation of some of these algorithms in homework problems as well as for the final project using datasets related to civil engineering applications.
Learning outcomes of the learning unit
By the end of this class, you will:
- See the potential of applying AI and ML tools.
- Know the most common ML techniques.
- Know how to implement ML techniques in python using popular data science libraries.
- Have all the tools needed to start an ML project on your own.
- Be able to read ML literature.
Prerequisite knowledge and skills
The main prerequisite for the class is a willingness to learn. Previous exposure to probability theory and linear algebra is advantageous but not critical for the success in the class. Some experience in scientific computing is good to have as the class does have an involved programming component. As such, the flavor of this class is applied with key theoretical concepts sprinkled in.
Planned learning activities and teaching methods
Interactive lectures followed by hands-on practical exercises.
Mode of delivery (face to face, distance learning, hybrid learning)
Blended learning
Further information:
Predominantly the lectures will be in person, but some components may have to be done online. For instance, invited lecture by ML practitioners from Silicon Valley will be via web conferencing. We will adapt as needed throughout the semester.
Course materials and recommended or required readings
Platform(s) used for course materials:
- eCampus
Further information:
Will be communicated in class and shared through e-campus. You do not need to buy any course materials.
Written work / report
Continuous assessment
Further information:
Your understanding of the subject material will be assessed/reinforced through homework assignments and the final class project. These two components contribute to your final grade, there is no final exam. The objective is that you work continuously throughout the semester without stress in the end.
Work placement(s)
Organisational remarks and main changes to the course
This class if offered in English.
Contacts
Instructor: Prof. Nenad Bijelic (nenad.bijelic@uliege.be)