Results 11  20
of
30
Synthesizing Learners Tolerating Computable Noisy Data
 In Proc. 9th International Workshop on Algorithmic Learning Theory, Lecture
, 1998
"... An index for an r.e. class of languages (by definition) generates a sequence of grammars defining the class. An index for an indexed family of languages (by definition) generates a sequence of decision procedures defining the family. F. Stephan's model of noisy data is employed, in which, roughly, c ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
An index for an r.e. class of languages (by definition) generates a sequence of grammars defining the class. An index for an indexed family of languages (by definition) generates a sequence of decision procedures defining the family. F. Stephan's model of noisy data is employed, in which, roughly, correct data crops up infinitely often, and incorrect data only finitely often. In a completely computable universe, all data sequences, even noisy ones, are computable. New to the present paper is the restriction that noisy data sequences be, nonetheless, computable! Studied, then, is the synthesis from indices for r.e. classes and for indexed families of languages of various kinds of noisetolerant languagelearners for the corresponding classes or families indexed, where the noisy input data sequences are restricted to being computable. Many positive results, as well as some negative results, are presented regarding the existence of such synthesizers. The main positive result is surpris...
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.
Learning in Friedberg Numberings
 Algorithmic Learning Theory: 18th International Conference, ALT 2007, Sendai, Japan, 2007, Proceedings. Springer, Lecture Notes in Artificial Intelligence
"... Abstract. In this paper we consider learnability in some special numberings, such as Friedberg numberings, which contain all the recursively enumerable languages, but have simpler grammar equivalence problem compared to acceptable numberings. We show that every explanatorily learnable class can be l ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
Abstract. In this paper we consider learnability in some special numberings, such as Friedberg numberings, which contain all the recursively enumerable languages, but have simpler grammar equivalence problem compared to acceptable numberings. We show that every explanatorily learnable class can be learnt in some Friedberg numbering. However, such a result does not hold for behaviourally correct learning or finite learning. One can also show that some Friedberg numberings are so restrictive that all classes which can be explanatorily learnt in such Friedberg numberings have only finitely many infinite languages. We also study similar questions for several properties of learners such as consistency, conservativeness, prudence, iterativeness and non Ushaped learning. Besides Friedberg numberings, we also consider the above problems for programming systems with Krecursive grammar equivalence problem. 1
Results on MemoryLimited UShaped Learning
"... Abstract. Ushaped learning is a learning behaviour in which the learner first learns a given target behaviour, then unlearns it and finally relearns it. Such a behaviour, observed by psychologists, for example, in the learning of pasttenses of English verbs, has been widely discussed among psychol ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
Abstract. Ushaped learning is a learning behaviour in which the learner first learns a given target behaviour, then unlearns it and finally relearns it. Such a behaviour, observed by psychologists, for example, in the learning of pasttenses of English verbs, has been widely discussed among psychologists and cognitive scientists as a fundamental example of the nonmonotonicity of learning. Previous theory literature has studied whether or not Ushaped learning, in the context of Gold’s formal model of learning languages from positive data, is necessary for learning some tasks. It is clear that human learning involves memory limitations. In the present paper we consider, then, the question of the necessity of Ushaped learning for some learning models featuring memory limitations. Our results show that the question of the necessity of Ushaped learning in this memorylimited setting depends on delicate tradeoffs between the learner’s ability to remember its own previous conjecture, to store some values in its longterm memory, to make queries about whether or not items occur in previously seen data and on the learner’s choice of hypotheses space. 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, correc ..."
Abstract

Cited by 4 (4 self)
 Add to MetaCart
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
Machine induction without revolutionary changes in hypothesis size
 Information and Computation
, 1996
"... This paper provides a beginning study of the effects on inductive inference of paradigm shifts whose absence is approximately modeled by various formal approaches to forbidding large changes in the size of programs conjectured. One approach, called severely parsimonious, requires all the programs co ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
This paper provides a beginning study of the effects on inductive inference of paradigm shifts whose absence is approximately modeled by various formal approaches to forbidding large changes in the size of programs conjectured. One approach, called severely parsimonious, requires all the programs conjectured on the way to success to be nearly (i.e., within a recursive function of) minimal size. It is shown that this very conservative constraint allows learning infinite classes of functions, but not infinite r.e. classes of functions. Another approach, called nonrevolutionary, requires all conjectures to be nearly the same size as one another. This quite conservative constraint is, nonetheless, shown to permit learning some infinite r.e. classes of functions. Allowing up to one extra bounded size mind change towards a final program learned certainly doesn’t appear revolutionary. However, somewhat surprisingly for scientific (inductive) inference, it is shown that there are classes learnable with the nonrevolutionary constraint (respectively, with severe parsimony), up to (i + 1) mind changes, and no anomalies, which classes cannot be learned with no size constraint, an unbounded, finite number of anomalies in the final program, but with no more than i mind changes. Hence, in some cases, the possibility of one extra mind change is considerably more liberating than removal of very conservative size shift constraints. The proofs of these results are also combinatorially interesting. 1
Variations on Ushaped learning
 IEEE Trans. Instrum. Meas
, 2005
"... The paper deals with the following problem: is returning to wrong conjectures necessary to achieve full power of algorithmic learning? Returning to wrong conjectures complements the paradigm of Ushaped learning [3,7,9,24,29] when a learner returns to old correct conjectures. We explore our problem ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
The paper deals with the following problem: is returning to wrong conjectures necessary to achieve full power of algorithmic learning? Returning to wrong conjectures complements the paradigm of Ushaped learning [3,7,9,24,29] when a learner returns to old correct conjectures. We explore our problem for classical models of learning in the limit from positive data: explanatory learning (when a learner stabilizes in the limit on a correct grammar) and behaviourally correct learning (when a learner stabilizes in the limit on a sequence of correct grammars representing the target concept). In both cases we show that returning to wrong conjectures is necessary to achieve full learning power. In contrast, one can modify learners (without losing learning power) such that they never show inverted Ushaped learning behaviour, that is, never return to old wrong conjecture with a correct conjecture inbetween. Furthermore, one can also modify a learner (without losing learning power) such that it does not return to old “overinclusive ” conjectures containing nonelements of the target language. We also consider our problem in the context of vacillatory
Control Structures in Hypothesis Spaces: The Influence on Learning
"... . In any learnability setting, hypotheses are conjectured from some hypothesis space. Studied herein are the effects on learnability of the presence or absence of certain control structures in the hypothesis space. First presented are control structure characterizations of some rather specific but ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
. In any learnability setting, hypotheses are conjectured from some hypothesis space. Studied herein are the effects on learnability of the presence or absence of certain control structures in the hypothesis space. First presented are control structure characterizations of some rather specific but illustrative learnability results. Then presented are the main theorems. Each of these characterizes the invariance of a learning class over hypothesis space V (and a little more about V ) as: V has suitable instances of all denotational control structures. 1 Introduction In any learnability setting, hypotheses are conjectured from some hypothesis space, for example, in [OSW86] from general purpose programming systems, in [ZL95, Wie78] from subrecursive systems, and in [Qui92] from very simple classes of classificatory decision trees. 3 Much is known theoretically about the restrictions on learning power resulting from restricted hypothesis spaces [ZL95]. In the present paper we begin to...
Prudence in vacillatory language identification
 Math. Systems Theory
, 1995
"... The present paper settles a question about ‘prudent ’ ‘vacillatory ’ identification of languages. Consider a scenario in which an algorithmic device M is presented with all and only the elements of a language L, and M conjectures a sequence, possibly infinite, of grammars. Three different criteria f ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
The present paper settles a question about ‘prudent ’ ‘vacillatory ’ identification of languages. Consider a scenario in which an algorithmic device M is presented with all and only the elements of a language L, and M conjectures a sequence, possibly infinite, of grammars. Three different criteria for success of M on L have been extensively investigated in formal language learning theory. If M converges to a single correct grammar for L, then the criterion of success is Gold’s seminal notion of TxtExidentification. If M converges to a finite number of correct grammars for L, then the criterion of success is called TxtFexidentification. And, if M, after a finite number of incorrect guesses, outputs only correct grammars for L (possibly infinitely many distinct grammars), then the criterion of success is known as TxtBcidentification. A learning machine is said to be prudent according to a particular criterion of success just in case the only grammars it ever conjectures are for languages that it can learn according to that criterion. This notion was introduced by Osherson, Stob, and Weinstein with a view to investigate certain proposals for characterizing natural languages in linguistic theory. Fulk showed that prudence does not restrict TxtExidentification, and later Kurtz and Royer showed that prudence does not restrict TxtBcidentification. The present paper shows that prudence does not restrict TxtFexidentification. 1
Report: Bertelsmann wants all of Napster. http://www.usatoday.com/life/cyber/invest/2002/04/05/napster.htm
 Algorithmic Learning Theory, 18th International Conference, ALT 2007, Springer Lecture Notes in Artificial Intelligence 4754:64–78
, 2002
"... Abstract. This work extends studies of Angluin, Lange and Zeugmann on the dependence of learning on the hypotheses space chosen for the class. In subsequent investigations, uniformly recursively enumerable hypotheses spaces have been considered. In the present work, the following four types of learn ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Abstract. This work extends studies of Angluin, Lange and Zeugmann on the dependence of learning on the hypotheses space chosen for the class. In subsequent investigations, uniformly recursively enumerable hypotheses spaces have been considered. In the present work, the following four types of learning are distinguished: classcomprising (where the learner can choose a uniformly recursively enumerable superclass as hypotheses space), classpreserving (where the learner has to choose a uniformly recursively enumerable hypotheses space of the same class), prescribed (where there must be a learner for every uniformly recursively enumerable hypotheses space of the same class) and uniform (like prescribed, but the learner has to be synthesized effectively from an index of the hypothesis space). While for explanatory learning, these four types of learnability coincide, some or all are different for other learning criteria. For example, for conservative learning, all four types are different. Several results are obtained for vacillatory and behaviourally correct learning; three of the four types can be separated, however the relation between prescribed and uniform learning remains open. It is also shown that every (not necessarily uniformly recursively enumerable) behaviourally correct learnable class has a prudent learner, that is, a learner using a hypotheses space such that it learns every set in the hypotheses space. Moreover the prudent learner can be effectively built from any learner for the class. 1