Sciweavers

MEMICS
2010
13 years 6 months ago
On Reliability and Refutability in Nonconstructive Identification
Identification in the limit, originally due to Gold [10], is a widely used computation model for inductive inference and human language acquisition. We consider a nonconstructive ...
Ilja Kucevalovs
COLT
2010
Springer
13 years 9 months ago
Strongly Non-U-Shaped Learning Results by General Techniques
In learning, a semantic or behavioral U-shape occurs when a learner rst learns, then unlearns, and, nally, relearns, some target concept (on the way to success). Within the framew...
John Case, Timo Kötzing
TCS
2010
13 years 9 months ago
Incremental learning with temporary memory
In the inductive inference framework of learning in the limit, a variation of the bounded example memory (Bem) language learning model is considered. Intuitively, the new model co...
Sanjay Jain, Steffen Lange, Samuel E. Moelius, San...
ECCC
2008
117views more  ECCC 2008»
13 years 11 months ago
The complexity of learning SUBSEQ(A)
Higman essentially showed that if A is any language then SUBSEQ(A) is regular, where SUBSEQ(A) is the language of all subsequences of strings in A. Let s1, s2, s3, . . . be the sta...
Stephen A. Fenner, William I. Gasarch, Brian Posto...
COLT
1992
Springer
14 years 3 months ago
Language Learning from Stochastic Input
Language learning from positive data in the Gold model of inductive inference is investigated in a setting where the data can be modeled as a stochastic process. Specifically, the...
Shyam Kapur, Gianfranco Bilardi
CIE
2007
Springer
14 years 5 months ago
Input-Dependence in Function-Learning
In the standard model of inductive inference, a learner gets as input the graph of a function, and has to discover (in the limit) a program for the function. In this paper, we cons...
Sanjay Jain, Eric Martin, Frank Stephan
LATA
2009
Springer
14 years 6 months ago
Hypothesis Spaces for Learning
In this paper we survey some results in inductive inference showing how learnability of a class of languages may depend on hypothesis space chosen. We also discuss results which co...
Sanjay Jain
ALT
2001
Springer
14 years 8 months ago
Learning by Switching Type of Information
The present work is dedicated to the study of modes of data-presentation in the range between text and informant within the framework of inductive inference. In this study, the le...
Sanjay Jain, Frank Stephan