%0 Journal Article 
%A García Laencina, Pedro José
%A Verdú Monedero, Rafael
%A Sancho Gómez, José Luis
%T Aprendizaje multitarea mediante arquitecturas neuronales basadas en subredes privadas
%D 2005
%U http://hdl.handle.net/10317/702
%X Human learning frequently involves learning several
tasks simultaneously; in particular, humans compare and
contrast similar tasks for solving a problem. Nevertheless, most
approaches to machine learning focus on the learning of a single
isolated task, Single Task Learning (STL). Most of them can be
formulated from learning several tasks related to the main task
at the same time while using a shared representation, Multitask
Learning (MTL). This type of learning improves generalization
performance for a main task by using the information contained
in other related tasks. In this article, we examine distinct schemes
used in MTL, propose an new network architecture and test each
scheme in two different problems. The proposed scheme makes
use of private subnetworks to improve the performance of MTL.
%K Teoría de la Señal y las Comunicaciones
%K Modelos duales
%K Aprendizaje multitarea
%K Arquitecturas neuronales
%K Arquitectura asimétrica
%~ GOEDOC, SUB GOETTINGEN