Learning Languages from Positive Data and a Finite Number of Queries

Jain, Sanjay; Kinber, Efim

doi:10.1007/978-3-540-30538-5_30

Cited by 8 publications

(50 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since a query learner identifies the target concept with just a single hypothesis, we allude to this scheme as one-shot learning. 4 Recently, the combination of these two approaches [11,12] as well as the common features of learners in either model [14,15] have gained interest in the learning theory community. [14,15] contributes a systematic analysis of common features of both approaches, thereby focussing on the identification of formal languages, ranging over indexable classes of recursive languages, as target concepts, see [2,13,19].…”

Section: Introductionmentioning

confidence: 99%

Gold-Style and Query Learning Under Various Constraints on the Target Class

Jain

Lange

Zilles

2005

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. In language learning, strong relationships between Gold-style models and query models have recently been observed: in some quite general setting Gold-style learners can be replaced by query learners and vice versa, without loss of learning capabilities. These 'equalities' hold in the context of learning indexable classes of recursive languages. Former studies on Gold-style learning of such indexable classes have shown that, in many settings, the enumerability of the target class and the recursiveness of its languages are crucial for learnability. Moreover, studying query learning, non-indexable classes have been mainly neglected up to now. So it is conceivable that the recently observed relations between Gold-style and query learning are not due to common structures in the learning processes in both models, but rather to the enumerability of the target classes or the recursiveness of their languages. In this paper, the analysis is lifted onto the context of learning arbitrary classes of r.e. languages. Still, strong relationships between the approaches of Gold-style and query learning are proven, but there are significant changes to the former results. Though in many cases learners of one type can still be replaced by learners of the other type, in general this does not remain valid vice versa. All results hold even for learning classes of recursive languages, which indicates that the recursiveness of the languages is not crucial for the former 'equality' results. Thus we analyse how constraints on the algorithmic structure of the target class affect the relations between two approaches to language learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Gold-Style and Query Learning Under Various Constraints on the Target Class

Jain

Lange

Zilles

2005

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is based on the philosophy that parents often correct their children by providing them counterexamples. This part is based on work done by the authors 13,12 . We also introduce and briefly consider a model in which learners are provided with random negative examples.…”

mentioning

confidence: 99%

Negative Data in Learning Languages

Jain¹,

Kinber²

2006

Mathematical Logic in Asia

Self Cite

View full text Add to dashboard Cite

The paper is a survey of recent results on algorithmic learning (inductive inference) of languages from full collection of positive examples and some negative data. Different types of negative data are considered. We primarily concentrate on learning using (1) carefully chosen finite negative data (2) negative counterexamples provided when conjectures contain data not in the target language (3) negative counterexamples obtained from a teacher (formally, oracle), when a learner queries the oracle if an hypothesis is contained in the target language. We also explore how least counterexamples and counterexamples of bounded size fair against arbitrary counterexamples. The effects of random negative data are also briefly considered.

show abstract

“…Following [JK05a] and [JK05b], we also consider Res variants for models SubQ n , NC n , and GNC n as well as their variants when the least (rather than arbitrary) counterexample is provided -in this case we use the prefix L (for example, LNC n ). Consequently, we explore relationships between B-models and models using limited number of queries (including those getting just answers 'yes' or 'no'), or limited number of arbitrary or least counterexamples, or just answers 'no'.…”

Section: Introductionmentioning

confidence: 99%

“…-the learner makes subset query for every conjecture until n negative answers have been received; that is, the learner can ask potentially indefinite number of questions (however, still finite if the learning process eventually gives a correct grammar), but he is charged only when receiving a negative answer; this model was considered in [JK05b] under the name NC n ;…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On Learning Languages from Positive Data and a Limited Number of Short Counterexamples

Jain

Kinber

2006

Learning Theory

Self Cite

View full text Add to dashboard Cite

We consider two variants of a model for learning languages in the limit from positive data and a limited number of short negative counterexamples (counterexamples are considered to be short if they are smaller that the largest element of input seen so far). Negative counterexamples to a conjecture are examples which belong to the conjectured language but do not belong to the input language. Within this framework, we explore how/when learners using n short (arbitrary) negative counterexamples can be simulated (or simulate) using least short counterexamples or just 'no' answers from a teacher. We also study how a limited number of short counterexamples fairs against unconstrained counterexamples, and also compare their capabilities with the data that can be obtained from subset, superset, and equivalence queries (possibly with counterexamples). A surprising result is that just one short counterexample can sometimes be more useful than any bounded number of counterexamples of arbitrary size. Most of results exhibit salient examples of languages learnable or not learnable within corresponding variants of our models.

show abstract

Learning Languages from Positive Data and a Finite Number of Queries

Cited by 8 publications

References 18 publications

Gold-Style and Query Learning Under Various Constraints on the Target Class

Gold-Style and Query Learning Under Various Constraints on the Target Class

Negative Data in Learning Languages

On Learning Languages from Positive Data and a Limited Number of Short Counterexamples

Contact Info

Product

Resources

About