This paper focuses on a logical model of induction, and specifically of
the common machine learning task of inductive concept learning (ICL). We define
an inductive derivation relation, which characterizes which hypothesis can be
induced from sets of examples, and show its properties. Moreover, we will also
consider the problem of communicating inductive inferences between two agents,
which corresponds to the multi-agent ICL problem. Thanks to the introduced logical
model of induction, we will show that this communication can be modeled
using computational argumentation.
Links:
[1] http://www.iiia.csic.es/en/individual/santiago-ontanon
[2] http://www.iiia.csic.es/en/individual/pilar-dellunde
[3] http://www.iiia.csic.es/en/individual/lluis-godo
[4] http://www.iiia.csic.es/en/individual/enric-plaza
[5] http://www.iiia.csic.es/en/publications/keyword/Induction
[6] http://www.iiia.csic.es/en/publications/keyword/Logic
[7] http://www.iiia.csic.es/en/publications/keyword/Argumentation
[8] http://www.iiia.csic.es/en/publications/keyword/Machine Learning
[9] http://www.iiia.csic.es/en/publications/export/tagged/3839
[10] http://www.iiia.csic.es/en/publications/export/xml/3839
[11] http://www.iiia.csic.es/en/publications/export/bib/3839
[12] http://www.iiia.csic.es/en/project/arinf
[13] http://www.iiia.csic.es/en/project/at
[14] http://www.iiia.csic.es/en/project/locomotion-0
[15] http://www.iiia.csic.es/en/project/next-cbr