Publications

Towards a logical model of induction from examples and communication

Publication Type:

Conference Paper

Authors:

Santiago Ontañón; Pilar Dellunde; Lluís Godo; Enric Plaza

Source:

Artificial Intelligence Research and Development, CCIA'10, IOS Press, p.259-268 (2010)

Keywords:

Induction; Logic; Argumentation; Machine Learning

Abstract:

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.

Projects: 
ARINF
AT
LOCOMOTION
Next-CBR
»