Case-Based Representation and Learning of Pattern Languages

@article{Jantke1993CaseBasedRA,
  title={Case-Based Representation and Learning of Pattern Languages},
  author={Klaus P. Jantke and Steffen Lange},
  journal={Theor. Comput. Sci.},
  year={1993},
  volume={137},
  pages={25-51}
}

On case-based learnability of languages

TLDR
The general approach to case-based learnability of indexable classes of formal languages is prototypically applied to so-called containmet decision lists, since they seem particularly tailored to cases represented in the form of particular cases with an appropriate similarity measure.

Inductive Bias in Case-Based Reasoning

TLDR
How this study has demonstrated, in the context of case-based learning, the operation of concepts well known in machine learning such as inductive bias and the trade-oo between computational complexity and sample complexity is discussed.

Logical Case Memory Systems: Foundations and Learning Issues Forschungsbericht Autor(en) / Author(s)

TLDR
The present development of the target concepts is accompanied by an in-depth discussion of related learning problems, allowing for the derivation of some basic results about the power and limitations of case-based learning.

Formalising the Knowledge Content of Case Memory Systems

TLDR
A ‘case-base semantics’ is presented which generalises recent formalisations of case-based classification and explores various issues in assuring that these semantics are well-defined, and illustrates how the knowledge content of the case memory system can be seen to reside in both the chosen similarity measure and in the cases of the Case-base.

Advances in Learning Formal Languages

TLDR
An overview in the advances related to the learning of formal languages i.e. development in the grammatical inference research is presented, and the case of context-free grammars, challenges, recent trends etc., is cited.

Learning in Case-Based Classification Algorithms

TLDR
This work transforms a simple symbolic learning algorithm (the version space algorithm) into an equivalent case-based variant and strengthens the conjecture of the equivalence of the learning power of symbolic and case-Based methods and shows the interdependency between the measure used by a case- based algorithm and the target concept.

On Learning Unions of Pattern Languages and Tree Patterns

TLDR
It is proved that if an arbitrary unions of pattern languages with fixed length substitutions can be learned efficiently then DNFs are efficiently learnable in the mistake bound model.

Solving Stabilization Problems in Case-Based Knowledge Acquisition

TLDR
A case study in case-based learning of learning containment decision lists from good examples, which contains a collection of theoretical results in the area of learnable examples.

Language Structure Using Fuzzy Similarity

TLDR
Using the fuzzy-similarity-based profile alignment, a methodology to formulate stochastic context-free grammar (CFG) rules is given and profile-alignment-based dynamic sentence similarity threshold is introduced to formulate the rules of stochastically CFG.

On Case-Based Representability and Learnability of Languages

TLDR
Within the present paper, case-based representability as well as case- based learnability of indexed families of uniformly recursive languages are investigated, both with respect to an arbitrary fixed similarity measure.

References

SHOWING 1-10 OF 30 REFERENCES

Case-based learning in inductive inference

TLDR
It is the author's intention to invoke inductive inference results for pointing to the crucial questions in case-based learning which allow to improve the power of case- based learning algorithms considerably.

Types of monotonic language learning and their characterization

TLDR
It is proved that strong-monotonic inference can be performed with iteratively learning devices without limiting the inference capabilities, while monotonic and weak-monotsonic inference cannot.

Monotonic Language Learning

  • S. Kapur
  • Linguistics, Computer Science
    ALT
  • 1992
TLDR
The ideas from inductive reasoning are instantiated in alternative ways, and links are established between the various new constraints both among themselves as well as with other well-known constraints, such as conservativeness.

Nonstandard Concepts of Similarity in Case-Based Reasoning

TLDR
Nonstandard concepts of similarity are introduced in a quite formal setting which allows an integration of well-known procedures like unification algorithms and may contribute to a considerable progress in the similarity-based use of cases.

Case-Based Learning Algorithms

TLDR
It is shown that some simple and generally applicable CBL algorithms can be deened that reduce storage requirements, tolerate noise, and tolerate irrelevant features.

Monotonic and Nonmonotonic Inductive Inference of Functions and Patterns

  • K. Jantke
  • Computer Science
    Nonmonotonic and Inductive Logic
  • 1990
TLDR
It turned out that in the area of inductive inference of total recursive functions monotonicity can rarely be guaranteed and these results are compared to the problem of inductively inferring text patterns from finite samples.

Polynomial Time Inference of General Pattern Languages

  • K. Jantke
  • Computer Science, Mathematics
    STACS
  • 1984
TLDR
The main result is a polynomial time algorithm constructing descriptive patterns of maximal length for the general case of patterns containing variable symbols from any finite set a priori fixed.

A Note on Polynominal-Time Inference of k-Variable Pattern Languages

  • Steffen Lange
  • Mathematics, Computer Science
    Nonmonotonic and Inductive Logic
  • 1990
TLDR
It is shown that, for every k, the whole family of k-variable pattern languages can be identified in the limit by a consistent polynomial-time strategy.

Language Identification in the Limit

  • E. M. Gold
  • Linguistics, Computer Science
    Inf. Control.
  • 1967