J-U.Kietz, K.Morik, "A Polynomial Approach to the Constructive Induction of Structural Knowledge". Machine Learning 14, pp 193-217, 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....constructed for bottom up construction of terminologies, because common properties of examples are deductively collected, but is unsuitable for rough and noisy data. The approach closest to the one presented in this paper is the constructive induction of structural knowledge of Kietz and Morik [KM94] who present a system KLUSTER which calculates most general discriminations (MGD) MGDs are generalised decision concepts which are optimal for the particular description logic presented in this paper and which is more expressive than our logic AL . The novelty of our method is that we present ....

J.-U. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14(2):193-218, 1994.

....Machine Learning workshop on Constructive Induction chaired by Matheus. Several papers in a recent special issue of Machine earning on Evaluating and Changing Representation examine constructive induction. For example, in that issue Wnek and Michalski [39] Wrobel [41] and Kietz and Morik [19] describe methods for dynamically shifting bias by performing constructive induction when learning fails. Furthermore, those papers address some of the same issues we focus on here. Rendell has done much work on this topic. The performance goals of Rendell s [27] constructive induction system are ....

Kietz, J. and Morik, K. (1994). A polynomial approach to the constructive induction of structured knowledge. Machine Learning, 14(2):193 218.

....for the msc. The pragmatic solution proposed in [9] is to restrict the length of value restriction chains occurring in the computed description by some arbitrary but fixed number. This way, one obtains an acyclic description, which may, however, be less specific than the real msc. Kietz and Morik [10] consider the problem of inductively learning concept descriptions from ABoxes. On the one hand, this work is more restrictive than ours since it does not allow for complex descriptions (not even acyclic ones) in the ABoxes. On the other hand, it tries to solve a more ambitious problem since it ....

J.-U. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning Journal, 14(2):193--218, 1994.

....8 Roughly speaking, query expansion amounts to computing all possible rewritings of a given query, given a terminological component TC and a horn clause component R. The field of Description Logics has raised increasing interest in the last few years in the Machine learning community. KM94] presents a constructive induction program named KLUSTER that uses a DL formalism to represent concept definitions. This DL is provided with a Least Common Subsumer algorithm. KLUSTER upgrades a T Box given examples represented as A Boxes, but it does not learn in a hybrid language target concept ....

J. U. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14(2):193--217, 1994.

....of predicates such as at least two, at most three, which can be viewed as operating upon the individual original user supplied predicates. Such systems have been used for research into correlating patient symptoms with diseases, and have been shown to excel ILP in their representational basis [Kietz and Morik, 1994]. In addition, Kietz and Morik, 1994] shows that such representations form one of the largest subsets of first order logic that is tractable under inductive inference. It has also been shown that ILP (with its logical representation language) is well suited for constructive induction [Srinivasan ....

.... at most three, which can be viewed as operating upon the individual original user supplied predicates. Such systems have been used for research into correlating patient symptoms with diseases, and have been shown to excel ILP in their representational basis [Kietz and Morik, 1994] In addition, [Kietz and Morik, 1994] shows that such representations form one of the largest subsets of first order logic that is tractable under inductive inference. It has also been shown that ILP (with its logical representation language) is well suited for constructive induction [Srinivasan and King, 1999a] by introducing ....

Kietz, J.-U. and Morik, K. (1994). A Polynomial Approach to the Constructive Induction of Structured Knowledge. Machine Learning, Vol. 14(1):pp. 193-- 217. Mining Scientific Data 40

....theory to give a formal base to the representation and reasoning system [6] Most DL learning stu is related with the computation of the Least Common Subsumer (LCS) introduced in [3] as an adaptation of Relative Least General Generalization to the DL eld. See for example [4, 7] The work of [11] by one hand, and [5] by another, try to acquire a whole theory (using the LCS computation as a subtask) All this DL work, and most ILP one have been done from a concept learning perspective. In this paper I establish a formal framework that addresses the problem of theory learning as a whole, ....

J. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14(2):193-217, 1994.

....the DL ALN including feature chains in order to approximate a disjunction operation which is not explicitly included in ALN . In addition, the operator is used as a subtask for the bottom up construction of knowledge bases based on the DLs ALN with cyclic concept definitions [1] See also [3] for a similar application concerning the constructive induction of a P Classic KB from data. In our applications, the LCS operation is used as a subtask for similaritybased information retrieval [5] The goal is to provide a user of an information system with an example based query mechanism. ....

J.U. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14:193--217, 1994.

....account. A preprocessing of descriptions would make it possible to determine a hierarchy of generalization of the numerical values. The creation of new values of attributes, as is the case in constructive induction, would make it possible to better account for the similarities between descriptions [18], 26] Acknowledgements The authors wish to specially thank the anonymous reviewers for their constructive reviews, suggestions and help for writing the final version of this paper. We also would like to thank Lise Fontaine for her careful proofreading of the final version. ....

Kietz J.U., Morik K.: A polynomial approach to the constructive induction of structural knowledge, Machine Learning 14(2), (1994). 193-217.

....for the DL ALN including feature chains in order to approximate a disjunction operation which is not explicitly included in ALN . In addition, the operator is used as a subtask for the bottom up construction of knowledge bases based on the DLs ALN with cyclic concept de nitions [1] See also [3] for a similar application concerning the constructive induction of a P Classic KB from data. In our applications, the LCS operation is used as a subtask for similaritybased information retrieval [5] The goal is to provide a user of an information system with an example based query mechanism. The ....

J.U. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14:193-217, 1994.

.... Works From the viewpoint of machine learning, a theory of logic based inductive inference has the strong relation with KDD[Fayyad et al. 1995; Shapiro et al. 1991] However utilized is only the scheme information but not characteristics of instances nor domain specific knowledge except a few[Kietz et al. 1994]. There is few research of temporal objects from this point of view to our knowledge. It is not easy to discover implicit conditions to give property values. Traditionally time series analysis is well known and applied to economics. But there is no research for the interaction between time series ....

Kietz,J.U. and Morik, K. A Polynomial Approach to the Constructive Induction of Structural Knowledge. Machine Learning 14 (1994).

.... of object applications constantly growing the need of analysis tools for object datasets becomes critical [7] Although the importance of the topic has been recognized [4, 1] it has been rarely addressed in the literature : a few studies concerning object knowledge representation (KR) systems [3, 9, 1], or object oriented (OO) databases [7] have been reported in the past years. Our own concern is the design of automatic class building tools for objects with complex relational structure. A compact class can be built on top of an object cluster discovered by an automatic clustering procedure ....

J.-U. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14(2):193--217, 1994.

....two or more individuals. Minimal descriptions are used for conceptual clustering and in database applications for schema generation and evolution, and as well, for query processing (as a kind of inexact matching) Conceptual clustering and induction of structural knowledge is also the subject of [ Kietz and Morik,1994 ] the goal is to build a hierarchy of concepts starting from a set of facts about some individuals. The building of the concept hierarchy is based on an operation similar to the lcs operation. In [ Coupey et al. 1997 ] and [ Salotti and Ventos,1997 ] classi cation (involving default and ....

J.-U. Kietz and K. Morik. A PolynomialApproach to the Constructive Induction of Structural Knowledge. Machine Learning, 14(2):193 217, 1994.

.... a combination of the two main approaches to represent and reason about relational knowledge, namely description logic (DL) and first order horn logic (HL) In Inductive Logic Programming (ILP) learning first order horn logic is investigated in depth, for learning DLs there exist first approaches [ Kietz and Morik, 1994; Cohen and Hirsh, 1994b ] and theoretical learnability results [ Cohen and Hirsh, 1994a; Frazier and Pitt, 1994 ] Recently, it was proposed to use Carin ALN as a framework for learning [ Rouveirol and Ventos, 2000 ] This is an interesting extension of ILP as provides a new bias orthogonal ....

Kietz, J.-U. and K. Morik: 1994, `A polynomial approach to the constructive Induction of Structural Knowledge'. Machine Learning 14(2), 193-- 217.

.... to represent and reason about relational knowledge, namely description logic (DL) and first order horn logic (HL) In Inductive Logic Programming (ILP) learning first order horn logic is investigated in depth, for learning DLs there exist first approaches and theoretical learnability results [ Kietz and Morik, 1994; Cohen and Hirsh, 1994; Frazier and Pitt, 1994 ] Recently, it was proposed to use Carin ALN as a framework for learning [ Rouveirol and Ventos, 2000 ] This is an interesting extension of ILP as provides a new bias orthogonal to the one used in ILP, i.e. it allows all quantified ....

Kietz, J.-U. and K. Morik: 1994, `A polynomial approach to the constructive Induction of Structural Knowledge'. Machine Learning 14(2), 193-- 217.

.... to represent and reason about relational knowledge, namely description logic (DL) and first order horn logic (HL) In Inductive Logic Programming (ILP) learning first order horn logic is investigated in depth, for learning DLs there exist first approaches and theoretical learnability results [ Kietz and Morik, 1994; Cohen and Hirsh, 1994; Frazier and Pitt, 1994 ] Recently, it was proposed to use Carin ALN as a framework for learning [ Rouveirol and Ventos, 2000 ] This is an interesting extension of ILP as provides a new bias orthogonal to the one used in ILP, i.e. it allows all quantified ....

Kietz, J.-U. and K. Morik: 1994, `A polynomial approach to the constructive Induction of Structural Knowledge'. Machine Learning 14(2), 193-- 217.

....of the two main approaches to represent and reason about relational knowledge, namely description logic and first order horn logic. In Inductive Logic Programming (ILP) learning first order horn logic is investigated in depth, for learning description logics there exist first approaches [Kietz and Morik, 1994; Cohen and Hirsh, 1994b] and theoretical learnability results [Cohen and Hirsh, 1994a; Frazier and Pitt, 1994] Recently, it was proposed to use CARIN 4 J fl as a framework for learning [Rouveirol and Ventos, 2000] This is a very interesting extension of ILP as 4 Jfprovides a new bias ....

Kietz, J.-U. and K. Morik: 1994, A polynomial approach to the constructive Induction of Structural Knowledge'. Machine Learning 14(2), 193-217.

No context found.

J-U.Kietz, K.Morik, "A Polynomial Approach to the Constructive Induction of Structural Knowledge". Machine Learning 14, pp 193-217, 1994.

No context found.

Kietz J.U., Morik K. A Polynomial Approach to the Constructive Induction of Structural Knowledge. Machine Learning, Vol. 14, pp. 193-217, 1994.

No context found.

J. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14(2):193-217, 1994.

No context found.

J.-U. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14(2):193--217, 1994.

No context found.

J.-U. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14(1):193--217, 1994.

No context found.

J. U. Kietz and K. Morik. A polynomialapproachto the constructive induction of structural knowledge. Machine Learning, 14(2):193--217, 1994.

No context found.

Kietz, J. U., Morik, K.: A Polynomial Approach to the Constructive Induction of Structural Knowledge. Machine Learning Journal,14(2). (1994) 193--218

No context found.

J.-U. Kietz and K. Morik. A polynomial approach to the constructive induction of structural knowledge. Machine Learning, 14(2):193--218, 1994.

No context found.

Kietz, J. and Morik, K. (1993). A polynomial approach to the constructive induction of structural knowledge. Machine Learning, to appear.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC