Imputación de datos incompletos y clasificación de patrones mediante aprendizaje multitarea
View/ Open
Identifiers
URI: http://hdl.handle.net/10317/703Share
Metrics
Statistics
View Usage StatisticsMetadata
Show full item recordKnowledge Area
Teoría de la Señal y las ComunicacionesSponsors
Este trabajo está parcialmente financiado por el Ministerio de Educación y Ciencia a través del proyecto TIC2002-03033.Publication date
2005-09Publisher
Universidad Politécnica de ValenciaBibliographic Citation
GARCÍA LAENCINA, Pedro José y SANCHO GÓMEZ, José Luis. Simposium Nacional de la Unión Científica Internacional (20º: 2005: Gandia) XX Simposium Nacional de la URSI 2005. URSI 05, Gandia 14-16 Septiembre 2005. Gandía: Universidad Politécnica de Valencia, 2005Keywords
Aprendizaje multitareaRedes neuronales artificiales
Esquema estándar MTL
Subredes
Abstract
Almost all research on supervised learning is based
on the assumption that training data are completely observable,
but it is not a common situation because real world databases are
rarely complete. The ability of handling missing data has become
a fundamental requirement for machine learning. Up to now,
proposed methods consider the problem as two separated tasks,
main task and imputation task, and solve them separately (Single
Task Learning, STL). In this paper, a new effective method is
proposed to handle missing features in incomplete databases with
Multitask Learning (MTL). This approach uses the imputation
task as extra task and learning in parallel with the main task.
Thus, imputation is guided and oriented by the learning process,
i.e., imputed values are those that contribute to improve the
learning. In this paper we use the advantages of MTL to handling
missing data and analyze its robustness for handling different
missing variables in real an artificial data sets.
Collections
The following license files are associated with this item:
Social media