Paper Info
Title
Learning from positive data based on the MINL strategy with refinement operators
Abstract
In the present paper we clarify the combination of the MINL (MINimal Langugae) strategy and refinement operators in the model of identification in the limit from positive data, by giving a learning procedure in a general form adopting both of the two. The MINL strategy is to choose minimal concepts consistent with given examples as guesses, and has been adopted in many previous works in the model. The minimality of concepts is defined w.r.t. the set-inclusion relation, and so the strategy is semantic-based. Refinement operators have developed in the field of learning logic programs to construct logic programs as hypotheses consistent with logical formulae given as examples. The operators are defined based on inference rules in first-order logic and so are syntactical. With the proposed procedure we give such a new class of tree pattern languages that every finite unions of the languages is identifiable from positive data without assuming the upperbound of the number of unions. Moreover, we revise the algorithm so that we can show that the class is polynomial time identifiable.
Year
DOI
Venue
2009
10.1007/978-3-642-14888-0_27
JSAI-isAI Workshops
Keywords
Field
DocType
general form,minimal langugae,minl strategy,refinement operator,new class,proposed procedure,first-order logic,positive data,finite union,logic program,polynomial time,pattern language,first order logic,inference rule
Concept class,New class,Theoretical computer science,Operator (computer programming),Artificial intelligence,Time complexity,Rule of inference,Mathematics,Tree pattern
Conference
Volume
ISSN
ISBN
6284
0302-9743
3-642-14887-5
Citations 
PageRank 
References 
2
0.40
14
Authors
2
Name
Order
Citations
PageRank
Seishi Ouchi120.74
Akihiro Yamamoto213526.84