International Workshop All '86 on Analogical and inductive inference
Learning regular sets from queries and counterexamples
Information and Computation
Monotonic and non-monotonic inductive inference
New Generation Computing - Selected papers from the international workshop on algorithmic learning theory,1990
Language learning in dependence on the space of hypotheses
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Journal of Computer and System Sciences
Automata on Infinite Objects and Church's Problem
Automata on Infinite Objects and Church's Problem
Avoiding coding tricks by hyperrobust learning
Theoretical Computer Science
Algorithmic Learning for Knowledge-Based Systems, GOSLER Final Report
Automatic Presentations of Structures
LCC '94 Selected Papers from the International Workshop on Logical and Computational Complexity
Automatic structures: overview and future directions
Journal of Automata, Languages and Combinatorics - Special issue: Selected papers of the workshop weighted automata: Theory and applications (Dresden University of Technology (Germany), March 4-8, 2002)
Formal language identification: query learning vs. gold-style learning
Information Processing Letters
Learning indexed families of recursive languages from positive data: A survey
Theoretical Computer Science
Robust separations in inductive inference
SFCS '90 Proceedings of the 31st Annual Symposium on Foundations of Computer Science
Learnability of automatic classes
LATA'10 Proceedings of the 4th international conference on Language and Automata Theory and Applications
Automatic learning of subclasses of pattern languages
Information and Computation
Automatic learners with feedback queries
Journal of Computer and System Sciences
Hi-index | 0.00 |
This paper adapts and investigates the paradigm of robust learning, originally defined in the inductive inference literature for classes of recursive functions, to learning languages from positive data. Robustness is a very desirable property, as it captures a form of invariance of learnability under admissible transformations on the object of study. The classes of languages of interest are automatic -- a formal concept that captures the notion of being recognisable by a finite automaton. A class of first-order definable operators -- called translators -- is introduced as natural transformations that preserve automaticity of languages in a given class and the inclusion relations between languages in the class. For many learning criteria, we characterise the classes of languages all of whose translations are learnable under that criterion. The learning criteria have been chosen from the literature on both explanatory learning from positive data and query learning, and include consistent and conservative learning, strong-monotonic learning, strong-monotonic consistent learning, finite learning, learning from subset queries, learning from superset queries, and learning from membership queries.