Olocip’s Artificial Intelligence models are possible thanks to the extensive database of different nature with which the different predictive models are trained.

The AI panel of experts is in charge of identifying and defining the selected variables to develop the appropriate algorithms in each situation. In this way, we are able to develop mathematical solutions that solve each problem with greater precision, which translates into innovative solutions in the market.

In this way, Olocip consists of the best experts in Artificial Intelligence such as Pedro Larrañaga, Concha Bielza, Marco Benjumeda and Sergio Luengo. These four scientists, within the framework of their activity as researchers at the Universidad Politécnica de Madrid, have been recognized by the publication of a scientific article in the prestigious journal Pattern Recognition (the sixth in the top 20 of the magazines Artificial Vision and Pattern Recognition). From our company we are proud of them and we want to recognize their new achievement.

The article titled “Tractable learning of Bayesian networks from partially observed data”, focuses mainly on learning probabilistic models, in particular Bayesian Networks, from incomplete data. In real-world problems, it is very common to find this type of data. A common cause is that certain information is not collected during the compilation of the data set. An example in the medical field is when the result of all possible tests for all patients is not available.


The most commonly used method for learning Bayesian Networks from incomplete data is the structural EM algorithm. The major limitation of this method is that it has a very high computational cost when applied to large datasets, which prevents its application to Big Data.

In this article, an alternative to this method is proposed that provides theoretical assurances regarding its efficiency. Furthermore, experiments suggest that the new proposal achieves better results than the structural EM algorithm and that it is more accurate in assigning values to incomplete data.

Pattern Recognition magazine was founded about 50 years ago, during the first years of computer expansion. It focuses on machine learning and also finds applications in areas such as biometrics, bioinformatics, multimedia data analysis and, more recently, data science. It is recognised as one of the most prestigious specialist journals in the field of Artificial Intelligence. Scopus currently classifies it as number 13 in the 168 JCR publications (indexed in the report on citations in scientific journals) of Artificial Intelligence and Google Scholar classifies it as the sixth in the top 20 of the journals of Artificial Vision and Pattern Recognition.

Full Article

Authors

Marco Benjumeda recieved his M.Sc. degree in Computer Science from the Autonomous University of Madrid in 2012. He obtained a M.Sc. degree in Artificial Intelligence from the Technical University of Madrid (UPM) in 2014 and is currently a Ph.D. student at UPM’s Artificial Intelligence Department and a member of the Computational Intelligence Group.

Sergio Luengo recieved his B.Sc. degree in Computer Science from the Alcalá de Henares University in 2013. He obtained a M.Sc. degree in Artificial Intelligence from the Technical University of Madrid (UPM) in 2014. He is currently a Ph.D. student at the UPM’s Artificial Intelligence Department and a member of the Computational Intelligence Group, taking part in the Cajal Blue Brain project. He also collaborates in the Human Brain Project developing software modules.

Pedro Larranaga is Full Professor in Computer Science and Artificial Intelligence at the Technical University of Madrid (UPM) since 2007. He received the MSc degree in mathematics (statistics) from the University of Valladolid and the PhD degree in computer science from the University of the Basque Country (”excellence award”). Before moving to UPM, his academic career has been developed at the University of the Basque Country (UPV-EHU) at several faculty ranks: Assistant Professor (1985–1998), Associate Professor (1998–2004) and Full Professor (2004–2007). He earned the habilitation qualification for Full Professor in 2003. He has published more than 200 papers in impact factor journals and has supervised 25 PhD theses. He is fellow of the European Association for Artificial Intelligence since 2012. He has been awared the 2013 Spanish National Prize in Computer Science and the prize of the Spanish Association for Artificial Intelligence in 2018

Concha Bielza received the M.S. degree in Mathematics from Universidad Complutense de Madrid, Madrid, Spain, in 1989 and the Ph.D. degree in Computer Science from Universidad Politécnica de Madrid, Madrid, in 1996 (extraordinary doctorate award). She is currently (since 2010) a Full Professor of Statistics and Operations Research with the Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid. She has published more than 100 papers in impact factor journals and has supervised 9 PhD theses. She was awared the 2014 UPM Research Prize.

Leave a comment

Your e-mail address will not be published. Required fields are marked *