After successfully completing this course, the student is able to:
- Apply machine learning techniques to tackle a practical problem
- Explain the essential concepts of supervised learning (classification and regression) and unsupervised learning (clustering), and categorize some popular algorithms
- Select and develop machine learning algorithms to apply to real-world data sets
- Understand and apply the essential data processing techniques (e.g. feature engineering) to real-world datasets
- Understand and interpret popular quality measures (e.g., Confusion matrix) to evaluate the performance of machine learning algorithms
- Explain the basic concepts of outlier detection and develop classification algorithms to detect outlier from real data
- Explain the main concepts of process mining and develop classification and linear regression algorithms to predict process performance and outcome
- Explain the basic concepts of natural language processing and develop clustering algorithms to identify topics from real text data
- Explain the main concepts of reinforcement learning and develop reinforcement learning algorithms to a given environment
- Collaborate in a team to tackle a data science project
- Use some popular machine learning libraries in python (e.g. scikit-learn)
In order to pass this course, you must receive at least a grade 6.0 for 3 out of 4 assignments and at least a grade 5.0 for the exam.
- Four group project assignment (50%)
- Individual written exam (50%)
- Successfully completed one of the following courses or show that you have adequate experience with programming
- Programmeren met Python (BETA-B1PYT)
- Computationeel denken (INFOB1CODE)
- It is strongly advised to have followed and completed the Data Analytics course.
This course focuses on the applications of machine learning algorithms to real-world questions.
The overall aim of this course is to provide the student with theories, techniques, tools, and practical experience for applying machine learning to tackle data science problems.
The course lectures cover five parts:
- Essential concepts and techniques of machine learning: classification, regression and clustering
- Application - Outlier detection
- Application - Predictive process mining
- Application - Natural language processing
- Application - Reinforcement learning
For each of the four application areas, you will work in a team to conduct an assignment that applies machine learning algorithms to a real-world dataset.
The course lectures are divided over nine weeks. Each week contains two lecture sessions and one tutorial session.
During the lectures, you will learn the theory, the concepts, and the algorithms.
During the tutorials, you will work on weekly exercises and four practical assignments.
Selected book chapters, articles, and lecture notes.