Polynomial-Time Identification of an Extension of Very Simple Grammars from Positive Data

2006 ◽  
pp. 45-58 ◽  
Author(s):  
Ryo Yoshinaka
Keyword(s):  
Polynomial Time ◽  
Positive Data

SIMPLE FLAT LANGUAGES: A LEARNABLE CLASS IN THE LIMIT FROM POSITIVE DATA

1999 ◽  
Vol 10 (04) ◽  
pp. 483-501
Author(s):  
OKADOME TAKESI
Keyword(s):  
Polynomial Time ◽  
Arithmetic Progression ◽  
Learning Algorithm ◽  
Finite Elasticity ◽  
Euclidean Algorithm ◽  
Context Sensitive ◽  
Positive Data ◽  
Context Free

The class of simple flat languages defined here is shonw to be learnable in the limit from positive data. In particular, its subclass named k-consecutive, which covers a part of the class of context-sensitive languages not belonging to the class of context-free languages, is polynomial-time learnable in the limit from positive data. The class of "disjunct" unions of simple flat languages is a nontrivial example which is learnable in the limit from positive data, but does not have Wright's finite elasticity. The learning algorithm presented here for identifying the subclasses of flat languages consists essentially of identifying an arithmetic progression in the limit from positive examples using Euclidean algorithm of mutual division.

Polynomial Time Inductive Inference of Cograph Pattern Languages from Positive Data

2012 ◽  
pp. 389-404 ◽  
Author(s):  
Yuta Yoshimura ◽  
Takayoshi Shoudai ◽  
Yusuke Suzuki ◽  
Tomoyuki Uchida ◽  
Tetsuhiro Miyahara
Keyword(s):  
Polynomial Time ◽  
Inductive Inference ◽  
Pattern Languages ◽  
Positive Data

Polynomial Time Inductive Inference of Ordered Tree Patterns with Internal Structured Variables from Positive Data

2002 ◽  
pp. 169-184 ◽  
Author(s):  
Yusuke Suzuki ◽  
Ryuta Akanuma ◽  
Takayoshi Shoudai ◽  
Tetsuhiro Miyahara ◽  
Tomoyuki Uchida
Keyword(s):  
Polynomial Time ◽  
Inductive Inference ◽  
Tree Patterns ◽  
Positive Data ◽  
Ordered Tree

FAMILIES OF NONCOUNTING LANGUAGES AND THEIR LEARNABILITY FROM POSITIVE DATA

1996 ◽  
Vol 07 (04) ◽  
pp. 309-327 ◽  
Author(s):  
SATOSHI KOBAYASHI ◽  
TAKASHI YOKOMORI
Keyword(s):  
Polynomial Time ◽  
Close Relation ◽  
Boolean Operations ◽  
Positive Data ◽  
Language Classes ◽  
Identification In The Limit ◽  
The Relationship

This paper introduces some subclasses of noncounting languages and presents some results on the learnability of the classes from positive data. We first establish several relationships among the language classes introduced and the class of reversible languages. Especially, we introduce the notion of local parsability, and define a class (k, l)-CLTS, which is a subclass of the class of concatenations of strictly locally testable languages. We show its close relation to the class of reversible languages. We then study on the relationship between the closure of the Boolean operations and the learnability in the limit from positive data only. Further, we explore the learnability question of some subclasses of noncounting languages in the model of identification in the limit from positive data. In particular, we show that, for each k, l≥1, (k, l)-CLTS is identifiable in the limit from positive data using reversible automata with the conjectures updated in polynomial time. Some possible applications of the result are also briefly discussed.

Polynomial Time Inductive Inference of Languages of Ordered Term Tree Patterns with Height-Constrained Variables from Positive Data

2017 ◽  
Vol E100.A (3) ◽  
pp. 785-802 ◽  
Author(s):  
Takayoshi SHOUDAI ◽  
Kazuhide AIKOH ◽  
Yusuke SUZUKI ◽  
Satoshi MATSUMOTO ◽  
Tetsuhiro MIYAHARA ◽  
...  
Keyword(s):  
Polynomial Time ◽  
Inductive Inference ◽  
Tree Patterns ◽  
Positive Data

scholarly journals Polynomial Time Inductive Inference of TTSP Graph Languages from Positive Data

2009 ◽  
Vol E92-D (2) ◽  
pp. 181-190 ◽  
Author(s):  
Ryoji TAKAMI ◽  
Yusuke SUZUKI ◽  
Tomoyuki UCHIDA ◽  
Takayoshi SHOUDAI
Keyword(s):  
Polynomial Time ◽  
Inductive Inference ◽  
Positive Data ◽  
Graph Languages
Sign in / Sign up

Export Citation Format

Share Document