A more effective vision of machine learning systems entails tools that are able to improve task after task and to reuse the patterns and knowledge that are acquired previously for future tasks. This incremental, long-life ...

The problem of estimating the class distribution (or prevalence) for a new unlabelled dataset (from a possibly different distribution) is a very common problem which has been addressed in one way or another in the past ...

Data mining is useful in making single decisions. The problem is when there are several related problems and the best local decisions do not make the best global result. We propose to calibrate each local data mining ...

[ES] La medicina actual, y todas las ciencias biomédicas y de la salud en general, se hallan inmersas en un cambio de paradigma. La cantidad de información relativa a pacientes que se maneja actualmente necesita de un ...

[ES] Esta tesis de maestría intenta trabajar con modelos de caja negra suponiendo que los datos originales no son disponible con el objetivo de determinar la importancia de la característica. Entonces, la idea es generar ...

In the field of learning models from data, the quality of models depends to a large extent on the quality of the training data. That is the reason why the preparation and cleaning of data is one of the stages of the knowledge ...

Este trabajo presenta un nuevo método de inducción de árboles de decisión, los Newton Trees (o Árboles de Estimación Estocástica de Probabilidades). Se trata de una redefinición de los árboles de decisión tradicionales ...

Distance-based and generalization-based methods are two families of artificial intelligence techniques that have been successfully used over a wide range of real-world problems. In the first case, general algorithms can ...

La resistencia a antimicrobianos es un problema actual e importante dentro del ámbito de salud. El uso de los antimicrobianos y la vigilancia de las resistencias son los dos focos clásicos donde se centran los esfuerzos ...

[EN] In this research project a series of experim ents were performed in order to infer the hierarchical structures of the classes from data that will be used to construct hierarchical classification models in various ...