Machine learning: Supervised methods
Course will address topics such as generalisation error analysis and estimation, optimisation and computational complexity, linear models, support vector machines and kernel methods, feature selection and sparsity, multi-class classification, ranking and multi-output learning.
Schedule:
–
Teaching time:
Daytime
Topic:
Information and communications technology
Form of learning:
Exam
Online
Provider:
Aalto University, FITech
Level:
Advanced
Credits:
5 By Aalto University (ECTS)
Fee:
€ 0.00
Application period:
1.6.2023
– 28.8.2023
Target group and prerequisites
Courses Machine Learning, Statistical inference or equivalent knowledge. Basics of probability theory and linear algebra. Programming skills. Mastering the prerequisite skills is very important in order to complete this course.Course description
Course contents
- Generalisation error analysis and estimation
- Model selection
- Optimisation and computational complexity
- Linear models
- Support vector machines and kernel methods
- Boosting
- Feature selection and sparsity
- Multilayer perceptrons
- Multi-class classification
- Ranking
- Multi-output learning
Learning outcomes
After the course, the student
- knows how to recognise and formalise supervised machine learning problems,
- knows how to implement basic optimisation algorithms for supervised learning problems,
- knows how to evaluate the performance supervised machine learning models,
- has understanding of the statistical and computational limits of supervised machine learning, as well as the principles behind commonly used machine learning models.
Teaching schedule
Lectures (Otaniemi) will be held on Tuesdays at 10:15-12:00. Exercise sessions (in Otaniemi) will be held on Fridays at 10:15-12:00. Attendance in lectures and exercise sessions is voluntary, recordings from lectures available. The exam is in Otaniemi.
Completion methods
Workload:
- 24 lecture hours
- 12 hours exercise session
- 3 hours exam
- 96 hours independent study
- Updated: