Advanced Topics on Knowledge Extration and Machine Learning
Keywords |
Classification |
Keyword |
OFICIAL |
Intelligent Systems |
Instance: 2016/2017 - 1S
Cycles of Study/Courses
Acronym |
No. of Students |
Study Plan |
Curricular Years |
Credits UCN |
Credits ECTS |
Contact hours |
Total Time |
PRODEI |
7 |
Syllabus |
1 |
- |
6 |
28 |
162 |
Teaching language
Suitable for English-speaking students
Objectives
Motivation
It is current practice of Corporations and Research Institutions to collect and store huge amounts of data.
The analysis of such data can become a competitive advantage (for business) or as a source for new discoveries (in research).
Analysing large amounts of data or complex data manual processes, or even OLAP, are prohibitive.
Computational tools, using data analysis algorithms (from Statistics, Machine Learning, Data Mining, etc.), are necessary for the [semi]-automatic construction of models that help decision makers and researchers to solve data-based complex problems.
Objectives
Motivate the students for the use of Data Mining techniques as decision support tools. Develop student's skills to correctly use DM techniques in the analysis of very large data sets. Make the students aware of advanced DM topics.
Learning outcomes and competences
It is expected the students to be able to:
- Know the different Data Mining problems.
- Identify decision making problems that can be represented as DM tasks.
- Know the stages of a DM project.
- Know the main methods/algorithms for each DM task and understand their workings. Special attention will be given to relational algorithms.
- Be able to apply those methods to decision problems.
- Be able to evaluate the results of a DM project.
Working method
Presencial
Pre-requirements (prior knowledge) and co-requirements (common knowledge)
Although it is not compulsory to have attended any specific course, it is advisable the student to have attended the courses: Introdução à estatística; and "Extração de Conhecimento e Aprendizagem Computacional". It is also relevant the student to have basic knowledge about algorithms.
Program
- Introduction to data mining
- Descriptive Data Mining
- Predictive Data Mining
- Evaluation of predictive models
- Meta-learning
- Visualization
- Recommender systems
- Text Mining
- Introduction to Multi-Relacional Data Mining
- Inductive Logic Programming
- Relacional Clustering
- Graph Mining
- Statistical Relational Learning
Mandatory literature
Jiawei Han, Micheline Kamber;
Data mining. ISBN: 1-55860-489-8
Lavrac N., and Dzeroski S.; Inductive Logic Programming: Techniques and Applications, 1994. ISBN: 0134578708
Complementary Bibliography
Ian H. Witten, Eibe Frank;
Data mining. ISBN: 1-55860-552-5
Peter Flach;
Machine Learning: The Art and Science of Algorithms that Make Sense of Data, Cambridge University Press, 2012. ISBN: 9781107422223 (http://www.cs.bris.ac.uk/~flach/mlbook/)
Mohammed Zaki and Wagner Meira Jr.;
Data Mining and Analysis: Fundamental Concepts and Algorithms, Cambridge University Press, 2013. ISBN: 9780521766333 (http://www.dcc.ufmg.br/miningalgorithms/DokuWiki/doku.php)
Max Kuhn, Kjell Johnson;
Applied Predictive Modeling, Springer New York, 2013. ISBN: 9781461468493
Jure Leskovec, Anand Rajaraman, Jeff Ullman; Mining of Massive Datasets, 2014. ISBN: 978-1107077232
Teaching methods and learning activities
Theoretical lectures to present the main Data Mining concepts.
Laboratory sessions to experiment with the taught concepts.
Software
Aleph ILP system
The R Project for Statistical Computing
RapidMiner 5
weka
Evaluation Type
Distributed evaluation without final exam
Assessment Components
Designation |
Weight (%) |
Trabalho laboratorial |
100,00 |
Total: |
100,00 |
Amount of time allocated to each course unit
Designation |
Time (hours) |
Estudo autónomo |
60,00 |
Frequência das aulas |
42,00 |
Trabalho laboratorial |
60,00 |
Total: |
162,00 |
Eligibility for exams
The "continuous evaluation" part of the final mark requires the student to make a practical work. Worker Students and equivalent, for which attending the classes is not compulsory, must arrange with the teacher periodic meetings to show the developments of their practical work. Their practical work presentation must be on the same day of regular students.
Calculation formula of final grade
Mark =
0.4 * project quality + 0.4 * report + 0.2 presentation and discussion of the projectExaminations or Special Assignments
Each student has to do is own practical project. The project includes the analysis of a data set, the writing of a report describing the work done and an oral presentation of the work.
Special assessment (TE, DA, ...)
All students have to do the practical work.
Classification improvement
Improving the continuous evaluation mark can only be done in the next year.