Course Description
The course is designed to introduce research at the intersection of
two areas in computer science: design and implementation of
programming languages, and data mining. Data mining is currently one
of the most vibrant and challenging fields of study in computer
science. The ever-growing heaps of ever more complex data that society
nowadays collects in every activity demand continuously for new ways
of exploring stored information. This opens up new opportunities but
also introduces new challenges, such as the ones opened by the need to
process multi-relational data. Formalisms based in Logic Programming,
such as Inductive Logic Programming, are widely seen as fundamental to
progress in this area.
This course therefore builds upon the expertise of the proponents to
propose an integrated view to this subject. We introduce the
foundations of Machine Learning and Data Mining, on the one hand, and
the foundations of Logic Programming, on other hand, and explain how
they can work together through Inductive Logic Programming. The
course has a strong research focus, and is geared at introducing the
student to recent progress in these exciting and quickly evolving
fields, such as the opening area of Statistical Relational Learning.
Prerequisites
Fundamental concepts on Probability Theory and Statistics, and Logic
are expected. Understanding of major Programming Language
implementation issues is recommended.
Expected Results
On completing the course, students should be able to:
- Identify data mining tasks, apply data mining algorithms and
evaluate their application.
- Have knowledge and understanding of the fundamental theoretic and
practical principals of logic programming concepts and
techniques.
- Have knowledge and understanding of the mechanisms needed to
achieve efficient implementation of logic programming
systems.
- Have the ability to design and implement prototype programs using
the systems presented during the course.
Classes
Concepts are introduced through standard lecturing with example
problems. Some classes can include laboratory work using some of the
systems presented during the course. Course material consist of
detailed slides and copies of key papers.
Lecturer Team
Alípio Mário Guedes Jorge.
Faculty of Economics, University of Porto.
Paulo Jorge Sousa Azevedo.
Department of Informatics, University of Minho.
Pavel Brazdil.
Faculty of Economics, University of Porto.
Ricardo Jorge Gomes Lopes da Rocha.
Department of Computer Science, Faculty of Sciences, University of Porto.
Rui Carlos Camacho de Sousa Ferreira da Silva.
Department of Electrical and Computer Engineering, Faculty of Engineering, University of Porto.
Vítor Manuel de Morais Santos Costa.
Department of Computer Science, Faculty of Sciences, University of Porto.