Incremental Learning from Positive Data

Lange, Steffen; Zeugmann, Thomas

doi:10.1006/jcss.1996.0051

Cited by 84 publications

(75 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main reason for hypothesis space not to be critical in many cases is that one can automatically convert the indices from one automatic family to another for the languages which are common to both automatic families. This stands in a contrast to the corresponding results for indexed families of recursive languages [25,26]. A result in the present work which depends on the choice of the hypothesis space is Theorem 18.…”

Section: Learning With Feedback and Memory Limitationscontrasting

confidence: 79%

“…Bounded example memory was considered by Osherson, Stob and Weinstein [28]; Lange and Zeugmann [25] extended this study. Wiehagen [33] and Lange and Zeugmann [25] introduced and studied feedback learning; Case, Jain, Lange and Zeugmann [8] quantified the amount of feedback queries per round.…”

Section: Learning With Feedback and Memory Limitationsmentioning

confidence: 79%

“…The following notion of feedback learning for general inductive inference was first studied by Wiehagen [33] and Lange and Zeugmann [25].…”

Section: Learning With Feedback and Memory Limitationsmentioning

confidence: 99%

“…The special case of iterative learning is quite popular and predates the definition of general memory limitations, it was introduced by Wiehagen [33] and later by Wexler and Culicover [32]. Bounded example memory was considered by Osherson, Stob and Weinstein [28]; Lange and Zeugmann [25] extended this study. Wiehagen [33] and Lange and Zeugmann [25] introduced and studied feedback learning; Case, Jain, Lange and Zeugmann [8] quantified the amount of feedback queries per round.…”

Section: Learning With Feedback and Memory Limitationsmentioning

confidence: 99%

See 3 more Smart Citations

Automatic learners with feedback queries

Case

Jain

Ong

et al. 2014

Journal of Computer and System Sciences

View full text Add to dashboard Cite

Abstract. Automatic classes are classes of languages for which a finite automaton can decide whether a given element is in a set given by its index. The present work studies the learnability of automatic families by automatic learners which, in each round, output a hypothesis and update a long term memory, depending on the input datum, via an automatic function, that is, via a function whose graph is recognised by a finite automaton. Many variants of automatic learners are investigated: where the long term memory is restricted to be the just prior hypothesis whenever this exists, cannot be of size larger than the size of the longest example or has to consist of a constant number of examples seen so far. Furthermore, learnability is also studied with respect to queries which reveal information about past data or past computation history; the number of queries per round is bounded by a constant. These models are generalisations of the model of feedback queries, given by Lange, Wiehagen and Zeugmann.

show abstract

Section: Learning With Feedback and Memory Limitationscontrasting

confidence: 79%

Section: Learning With Feedback and Memory Limitationsmentioning

confidence: 79%

“…The following notion of feedback learning for general inductive inference was first studied by Wiehagen [33] and Lange and Zeugmann [25].…”

Section: Learning With Feedback and Memory Limitationsmentioning

confidence: 99%

Section: Learning With Feedback and Memory Limitationsmentioning

confidence: 99%

See 2 more Smart Citations

Automatic learners with feedback queries

Case

Jain

Ong

et al. 2014

Journal of Computer and System Sciences

View full text Add to dashboard Cite

show abstract

“…The situation is comparable to Lange-Zeugmann's [13] bounded example memory learnability BEM k of languages from positive data, where BEM k yields an infinite hierarchy such that k∈N BEM k is a proper subclass of the class of all indexed families that can be conservatively learned.…”

Section: Hierarchy Resultsmentioning

confidence: 99%

Consistency Conditions for Inductive Inference of Recursive Functions

Akama

Zeugmann

2007

New Frontiers in Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Abstract. A consistent learner is required to correctly and completely reflect in its actual hypothesis all data received so far. Though this demand sounds quite plausible, it may lead to the unsolvability of the learning problem. Therefore, in the present paper several variations of consistent learning are introduced and studied. These variations allow a so-called δ-delay relaxing the consistency demand to all but the last δ data. Additionally, we introduce the notion of coherent learning (again with δ-delay) requiring the learner to correctly reflect only the last datum (only the n − δth datum) seen. Our results are threefold. First, it is shown that all models of coherent learning with δ-delay are exactly as powerful as their corresponding consistent learning models with δ-delay. Second, we provide characterizations for consistent learning with δ-delay in terms of complexity. Finally, we establish strict hierarchies for all consistent learning models with δ-delay in dependence on δ.

show abstract