Results 1  10
of
32
The Power of Vacillation in Language Learning
, 1992
"... Some extensions are considered of Gold's influential model of language learning by machine from positive data. Studied are criteria of successful learning featuring convergence in the limit to vacillation between several alternative correct grammars. The main theorem of this paper is that there ..."
Abstract

Cited by 48 (11 self)
 Add to MetaCart
(Show Context)
Some extensions are considered of Gold's influential model of language learning by machine from positive data. Studied are criteria of successful learning featuring convergence in the limit to vacillation between several alternative correct grammars. The main theorem of this paper is that there are classes of languages that can be learned if convergence in the limit to up to (n+1) exactly correct grammars is allowed but which cannot be learned if convergence in the limit is to no more than n grammars, where the no more than n grammars can each make finitely many mistakes. This contrasts sharply with results of Barzdin and Podnieks and, later, Case and Smith, for learnability from both positive and negative data. A subset principle from a 1980 paper of Angluin is extended to the vacillatory and other criteria of this paper. This principle, provides a necessary condition for circumventing overgeneralization in learning from positive data. It is applied to prove another theorem to the eff...
Synthesizing Enumeration Techniques For Language Learning
 In Proceedings of the Ninth Annual Conference on Computational Learning Theory
, 1996
"... this paper we assume, without loss of generality, that for all oe ` ø , [M(oe) 6=?] ) [M(ø) 6=?]. ..."
Abstract

Cited by 16 (7 self)
 Add to MetaCart
this paper we assume, without loss of generality, that for all oe ` ø , [M(oe) 6=?] ) [M(ø) 6=?].
Learning in the presence of inaccurate information
 in &quot;Proceedings of the 2nd Annual ACM Conference on Computational Learning Theory
, 1989
"... The present paper considers the effects of introducing inaccuracies in a learner’s environment in Gold’s learning model of identification in the limit. Three kinds of inaccuracies are considered: presence of spurious data is modeled as learning from a noisy environment, missing data is modeled as ..."
Abstract

Cited by 9 (3 self)
 Add to MetaCart
The present paper considers the effects of introducing inaccuracies in a learner’s environment in Gold’s learning model of identification in the limit. Three kinds of inaccuracies are considered: presence of spurious data is modeled as learning from a noisy environment, missing data is modeled as learning from incomplete environment, and the presence of a mixture of both spurious and missing data is modeled as learning from imperfect environment. Two learning domains are considered, namely, identification of programs from graphs of computable functions and identification of grammars from positive data about recursively enumerable languages. Many hierarchies and tradeoffs resulting from the interplay between the number of errors allowed in the final hypotheses, the number of inaccuracies in the data, the types of inaccuracies, and the type of success criteria are derived. An interesting result is that in the context of function learning, incomplete data is strictly worse for learning than noisy data. 1
Non UShaped Vacillatory and Team Learning
, 2008
"... Ushaped learning behaviour in cognitive development involves learning, unlearning and relearning. It occurs, for example, in learning irregular verbs. The prior cognitive science literature is occupied with how humans do it, for example, general rules versus tables of exceptions. This paper is most ..."
Abstract

Cited by 6 (2 self)
 Add to MetaCart
Ushaped learning behaviour in cognitive development involves learning, unlearning and relearning. It occurs, for example, in learning irregular verbs. The prior cognitive science literature is occupied with how humans do it, for example, general rules versus tables of exceptions. This paper is mostly concerned with whether Ushaped learning behaviour may be necessary in the abstract mathematical setting of inductive inference, that is, in the computational learning theory following the framework of Gold. All notions considered are learning from text, that is, from positive data. Previous work showed that Ushaped learning behaviour is necessary for behaviourally correct learning but not for syntactically convergent, learning in the limit ( = explanatory learning). The present paper establishes the necessity for the hierarchy of classes of vacillatory learning where a behaviourally correct learner has to satisfy the additional constraint that it vacillates in the limit between at most b grammars, where b ∈ {2, 3,...,∗}. Non Ushaped vacillatory learning is shown to be restrictive: every non Ushaped vacillatorily learnable class is already learnable in the limit. Furthermore, if vacillatory learning with the parameter b = 2 is possible then non Ushaped behaviourally correct learning is also possible. But for b = 3, surprisingly, there is a class witnessing that this implication fails.
Cooperation = Coordination + Solvability
, 2003
"... We advance and compare two families of coalitional paradigms of solvability. A coalitional ..."
Abstract

Cited by 6 (6 self)
 Add to MetaCart
We advance and compare two families of coalitional paradigms of solvability. A coalitional
Consistent Identification in the Limit of Some of Penn and Buszkowski's Classes is NPhard
, 1999
"... In (Buszkowski, 1987) and (Buszkowski and Penn, 1990) certain `discovery procedures' for classical categorial grammars were de ned. These procedures accept a sequence of structures (strings labeled with derivational information) as input and yield a set of hypotheses in the form of grammars. In ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
In (Buszkowski, 1987) and (Buszkowski and Penn, 1990) certain `discovery procedures' for classical categorial grammars were de ned. These procedures accept a sequence of structures (strings labeled with derivational information) as input and yield a set of hypotheses in the form of grammars. In (Kanazawa, 1998) learning functions based on these discovery procedures were studied, and it was shown that some of the classes associated with these procedures can be eectively identi ed in the limit from positive data. The time complexity of these functions however was still left an open question. In this paper I will show that learning functions for these classes that are responsive and consistent on their class and learn their class prudently are all NPhard.
Learning from Multiple Sources of Inaccurate Data
 in &quot;Proceedings of the International Workshop on Analogical and Inductive Inference in Dagstuhl
, 1992
"... Abstract. Most theoretical models of inductive inference make the idealized assumption that the data available to a learner is from a single and accurate source. The subject of inaccuracies in data emanating from a single source has been addressed by several authors. The present paper argues in favo ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
(Show Context)
Abstract. Most theoretical models of inductive inference make the idealized assumption that the data available to a learner is from a single and accurate source. The subject of inaccuracies in data emanating from a single source has been addressed by several authors. The present paper argues in favor of a more realistic learning model in which data emanates from multiple sources, some or all of which may be inaccurate. Three kinds of inaccuracies are considered: spurious data (modeled as noisy texts), missing data (modeled as incomplete texts), and a mixture of spurious and missing data (modeled as imperfect texts). Motivated by the above argument, the present paper introduces and theoretically analyzes a number of inference criteria in which a learning machine is fed data from multiple sources, some of which may be infected with inaccuracies. The learning situation modeled is the identification in the limit of programs from graphs of computable functions. The main parameters of the investigation are: kind of inaccuracy, total number of data sources, number of faulty data sources which produce data within an acceptable bound, and the bound on the number of errors allowed in the final hypothesis learned by the machine. Sufficient conditions are determined under which, for the same kind of inaccuracy, for the same
Notes on Formalizing Coordination
 AI*IA 99: Advanced in Arti Intelligence
, 2000
"... This paper concerns with 2agents coordination gameswe call them paradigms of coordination. To coordinate, agents' behaviour must eventually stabilize to a set of basic formulas that express a suitable part of agents' "nature". Four paradigms are advanced and discussed. Se ..."
Abstract

Cited by 5 (5 self)
 Add to MetaCart
(Show Context)
This paper concerns with 2agents coordination gameswe call them paradigms of coordination. To coordinate, agents' behaviour must eventually stabilize to a set of basic formulas that express a suitable part of agents' "nature". Four paradigms are advanced and discussed. Several new perspectives are provided to coordinating agents. Coordination via belief revision and cooperation by team work are two. 1
Vacillatory learning of nearly minimal size grammars
 Journal of Computer and System Sciences
, 1994
"... In Gold’s influential language learning paradigm a learning machine converges in the limit to one correct grammar. In an attempt to generalize Gold’s paradigm, Case considered the question whether people might converge to vacillating between up to (some integer) n> 1 distinct, but equivalent, cor ..."
Abstract

Cited by 4 (4 self)
 Add to MetaCart
(Show Context)
In Gold’s influential language learning paradigm a learning machine converges in the limit to one correct grammar. In an attempt to generalize Gold’s paradigm, Case considered the question whether people might converge to vacillating between up to (some integer) n> 1 distinct, but equivalent, correct grammars. He showed that larger classes of languages can be algorithmically learned (in the limit) by converging to up to n + 1 rather than up to n correct grammars. He also argued that, for “small ” n> 1, it is plausible that people might sometimes converge to vacillating between up to n grammars. The insistence on small n was motivated by the consideration that, for “large ” n, at least one of n grammars would be too large to fit in peoples ’ heads. Of course, even for Gold’s n = 1 case, the single grammar converged to in the limit may be infeasibly large. An interesting complexity restriction to make, then, on the final grammar(s) converged to in the limit is that they all have small size. In this paper we study some of the tradeoffs in learning power involved in making a welldefined version of this restriction. We show and exploit as a tool the desirable property that the learning power under our