First term
Second term
Both terms
This year
Next year
Alternating years
External
Prerequisites
Taught by
Language of instruction
Duration
LevelMachine Learning and Inductive Inference (B-KUL-H02C1A)
Cannot be taken as part of an examination contractAims
This course will familiarise the students with the domain of machine learning, which concerns techniques to build software that can learn how to perform a certain task (or improve its performance on it) by studying examples of how it has been accomplished previously, and in a broader sense the discovery of knowledge from observations (inductive inference).
After following this course, students will:
- have a basic understanding of the general principles of learning
- have an overview of the existing techniques for machine learning and data mining
- understand how these techniques work, and why they work
- be able to implement programs that learn or exhibit adaptive behavior, using these techniques
- be up-to-date with the current state of the art in machine learning research
- be able to contribute to contemporary machine learning research
Previous knowledge
Students should be familiar with:
- algorithms and programming
- some elements from higher mathematics, probability theory and statistics
- predicate logic
Introductory courses on these topics (at the Bachelor level) suffice.
Course material
Slides, transparencies, courseware
Toledo / e-platform
Syllabus
Order of Enrolment
This course unit is a prerequisite for taking the following course units:
H05N0A : Capita selecta computerwetenschappen: Artificiële intelligentie
Is also included in other courses
- Master in de statistiek (Biometrics) 120 ects.
-
Master in de toegepaste economische wetenschappen: handelsingenieur in de beleidsinformatica
120 ects.
- Master of Artificial Intelligence (Option: Engineering and Computer Science (ECS)) 60 ects.
-
Master of Bioinformatics
120 ects.
-
Master in de bio-informatica
120 ects.
- Master of Statistics (Biometrics) 120 ects.
-
Master of Information Management
60 ects.
Activities
1.0 ects. Machine Learning and Inductive Inference: Exercises (B-KUL-H00G6a)
Content
Exercises are made on the subjects discussed during the lectures. These are mostly pen-and-paper exercises where students gain insight in the workings of learning algorithms by manually mimicking the computations of certain learning algorithms, graphically describing the result of a learning algorithm (by drawing decision
surfaces), etc. There are also exercises on evaluation of machine learning models and algorithms.
Description of learning activities
Students try to independently solve the exercises during some time. A teaching assistant provides help where necessary, and discusses the solution afterwards.
Course material
- A list of exercises.
- Solutions are made available on Toledo.
3.0 ects. Machine Learning and Inductive Inference: Lecture (B-KUL-H02C1a)
Content
1. introduction to machine learning, connections with other subjects
2. general principles of learning:
- concept learning, version spaces
- evaluation of learning algorithms
- theory of learnability
- representation of inputs and outputs of learning algorithms
3. specific learning approaches:
- decision trees
- rules, association rules
- instance based learning
- clustering
- neural networks
- support vector machines
- Bayesian learning
- genetic algorithms
- ensemble methods (bagging, boosting, ...)
- reinforcement learning
- inductive logic programming
Description of learning activities
Ten lectures of 2 hours each.
Course material
Course Text
Lecture slides
Evaluation
Evaluation : Machine Learning and Inductive Inference (B-KUL-H22C1a)
Explanation
The exam consists of questions about the theory as well as some exercises. The course text and lecture slides can be consulted during the exam. Students have about 2 hours time for preparing their answers, followed by an ten minute oral interrogation.
