Esta asignatura expone las redes Bayesianas como herramientas gráficas bien consolidadas y de enorme aplicación en la actualidad para modelizar la incertidumbre y razonar con ella en sistemas inteligentes. La incertidumbre se modeliza con la probabilidad y el razonamiento se basa en la regla de Bayes.
Créditos ECTS: 5.
GENERAL DESCRIPTION OF THE SUBJECT
This module presents Bayesian Networks as graphical tools which are well consolidated and of wide use nowadays to model uncertainty and reason with in intelligent systems. Uncertainty is modelled with probabilities and reasoning is based on Bayes’ rule.
It begins by explaining the meaning of the networks to model how to reason under uncertainty, and both from a structural (qualitative) point of view and parametric (quantitative). The next step is to pose questions to the network, in other words, to infer knowledge from observations or data that is being collected. Thus, we can ask, for instance, for the diagnosis of a disease or the most likely explanation for the observed evidence. The algorithms can obtain the exact or an approximate answer, in the latter case probably using MonteCarlo simulation.
The network is built by analysing the problem with an expert, but can also be induced from a database. This is a current issue: how to obtain from data a structure and parameters for the network. Finally, by knowing how to build the network and how to use it to perform queries, it will be possible to see its application on decision making and other applications of great interest within Artificial Intelligence: computer vision, automatic classification, filtering of email, etc.
OBJETIVES: KNOWLEDGE AND SKILLS
- To be able to model real problems where uncertainty is an essential component by means of Bayesian Networks.
- To be able to recognise where the frontiers of knowledge are in Bayesian networks by means of critical reading of relevant scientific papers, usuallly written in English.
-To be able to contribute with new ideas, at the methodological level as well as in the application of Bayesian Networks, going beyond the frontiers of knowledge.
-To be able to express the ideas of the state of the art and newly contributed ideas, both orally and in writing.
EVALUATION ACTIVITIES OR PRACTICAL TASKS
Brief description of assessment activities
- To deliver two individual oral presentations about the state of the art based on module's content; one of them about inference, and the other one about learning. (weight on the final grade:60%).
- To write an individual assignmet, proposed by the student or the professor, which allows the student to study in depth a given subject related to the module's content. Innovative aspects of the work will be particularly valued. (weight on the final grade 40%)
Grades are given by assessing:
- To deliver two individual oral presentations about the state of the art based on module's content; one of them about supervised classification and the other one about unsupervised classification. Clarity when presenting and scope of the state of the art covered will be valued. This weighs 60% in the final grade.
- To write an individual assignment, proposed by the student or professor, which allows to go more deeply into some topic of the subject. Innovative aspects of the work will be particularly valued. The weight of this part is 40%.
Assessment for the extraordinary july examination will be similar (two oral presentations and an individual written assignment).