Course contents
- Exploratory data analysis
- Dimensionality reduction
- PCA
- Regression and classification
- Clustering
- Deep learning
- Reinforcement learning
- Language modeling
Learning outcomes
After completing the course, the students
- can formalise applications as ML problems and solve them using basic ML methods
- can perform basic exploratory data analysis
- understand the meaning of the train-validate-test approach in machine learning
- can apply standard regression and classification models on a given data set
- can apply simple clustering and dimensionality reduction techniques on a given data set
- are familiar with and can explain the basic concepts of reinforcement learning and language modeling.
Teaching methods
The course follows a schedule and includes lectures, self study, assignments, and a project work. The lectures are available online.
Teaching times on campus:
Lectures:
- Wednesdays at 14:15–16
- Fridays at 12:15–14
Exercises:
- Mondays at 8:15–10 (online)
- Tuesdays at 16:15–18
- Wednesdays at 8:15–10 (reserved for project support)
- Thursdays at 14:15–18
- Fridays at 14:15–16 (online)
Exam:
- 13.10.–31.10. in the Exam-room on Aalto University campus.
- Students are required to schedule a time slot (3 hours) during the opening hours of the Exam-rooms (excluding weekends). More information with a detailed schedule will be provided when the course starts.
Workload
Approx. 134 hours of work divided into:
- Lectures + self-study: 10*(2+2) = 40 hours
- Assignments: 5 * 9 =45 hours
- Project work: 30 hours
- Peer-grading: 8 hours
- Exam + preparation: 10 hours.
Completion methods
Assignments, project work and an exam on campus.
More information in the Aalto University study guide.
You can get a digital badge after completing this course.