A. Yamamoto and H. Arimura, "Inductive logic programming: from logic of discovery to machine learning," IEICE Trans. Inf. & Syst., E-83-D (1), pp.10--18, 2000.  Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Discovery and Deduction - Hagiya, Takahashi (2000) (Correct)
....restrictions, and to prune protocols by cheap tests before applying the protocol veri er. 3 Discovery for Deduction Reachability Computation and Learning from Positive Data The problem of synthesizing a loop invariant should have close relationship with that of learning from positive data [2, 5]. In this section, the problem of characterizing reachable states of a state transition system is discussed. This is a problem of nding a nite representation of the set of states that are reachable from an initial state. Assume a state transition system. Let S be the set of all states of the ....
....inductive inference, though we cannot ask queries in general. Arimura et al. formulated the procedure in Figure 8, which learns unions of at most k tree patterns using subset queries [4] This framework is considered to be an instance of the more general framework of learning from entailmant [5]. In particular, the generic algorithm for learning from entailmant proposed by Arimura and Yamamoto shows a close correspondence with our algorithm in Figure 6. This is because their algorithm only generates hypotheses that are subsets of the target language. In their algorithm in Figure 9, H ....
Hiroki Arimura and Akihiro Yamamoto. Inductive Logic Programming: From Logic of Discovery to Machine Learning. IEICE Transactions on Information and Systems, Vol.E83-D, No.1, pp.10-18, 2000.
Learning Term Rewriting Systems from Entailment - Arimura, Sakamoto, Arikawa (2000) Self-citation (Arimura) (Correct)
.... a number of efficient learnability results are obtained for various fragments of first order logic have been shown to be learnable using this framework [1, 4, 9 12, 15, 16] Recently, it is found that a class of learning algorithms for subclasses of first order Horn programs has a common scheme [16, 22], which has its origin in a monotone Boolean DNF learner in [18] Reddy and Tadepalli [16] proposed an algorithm with subsumption membership queries and saturation generalization. Yamamoto and Arimura [22] gave a generic bottom up learning algorithm (Fig. 1 in this paper) that learns a subclass of ....
....of learning algorithms for subclasses of first order Horn programs has a common scheme [16, 22] which has its origin in a monotone Boolean DNF learner in [18] Reddy and Tadepalli [16] proposed an algorithm with subsumption membership queries and saturation generalization. Yamamoto and Arimura [22] gave a generic bottom up learning algorithm (Fig. 1 in this paper) that learns a subclass of Horn programs using subsumption queries and entailment equivalent queries under a certain condition based on the works of Yamamoto on proof completion [19, 21] They have demonstrate that known efficient ....
A. Yamamoto and H. Arimura, "Inductive logic programming: from logic of discovery to machine learning," IEICE Trans. Inf. & Syst., E-83-D (1), pp.10--18, 2000.
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