Y. Mukouchi, Inductive inference with bounded mind changes, Proc. 3rd Workshop on Algorithmic Learning Theory (S. Doshita, K. Furukawa, K.P. Jantke and T. Nishida, Eds.), Springer-Verlag, Berlin, 1993, Lecture Notes in Artificial Intelligence 743, pp. 125 -- 134.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....(cf. e.g. Case and Lynes [12] Case [11] Fulk [14] Looking at potential applications, Angluin [1, 2] started the systematic study of learning enumerable families of uniformly recursive languages, henceforth called indexed families. Recently, this topic has attracted much attention (cf. e.g. [23, 24, 25, 27, 28, 29, 34, 38, 43]) Next we specify the information from which the target languages have to be learned. A text of a language L is an infinite sequence of strings that eventually contains all strings of L. Alternatively, one can consider learning from informant. An informant of a language L is an infinite sequence ....

....all the mentioned papers considered the learnability of recursive functions. Hence, it is only natural to ask whether or not this measure of efficiency is of equal importance in the setting of language learning. This is indeed the case as recently obtained results show (cf. e.g. Mukouchi [34, 35], Lange and Zeugmann [29] Lange [26] In this paper we study problems of higher granularity. In order to explain them we have to describe the monotonicity constraints and their dual counterparts we are going to deal with. The three notions of monotonicity reflect different formalizations of the ....

[Article contains additional citation context not shown here]

Mukouchi, Y.: Inductive inference with bounded mind changes. In Proceedings 3rd Workshop on Algorithmic Learning Theory, (S. Doshita, K. Furukawa, K.P. Jantke and T. Nishida, Eds.), Lecture Notes in Artificial Intelligence Vol. 743 (1992), pages 125 -- 134, Springer-Verlag, Berlin.

....from positive data that avoids overgeneralization. Finally, language learning with a bounded number of mind changes is completely characterized in terms of recursively generable finite sets. These characterizations offer a new method to handle overgeneralizations and resolve an open question of Mukouchi (1992). 1. Introduction Inductive inference is the process of hypothesizing a general rule from eventually incomplete data. It has its historical origins in the philosophy of science. However, within the last three decades it received much attention from computer scientists. Nowadays inductive ....

....of the author s paper at the 10th Annual Symposium on Theoretical Aspects of Computer Science, Lecture Notes in Computer Science 665, 682 691. y This research has been supported by the German Ministry for Research and Technology (BMFT) under grant no. 01 IW 101. 1 Lange and Zeugmann (1992) Mukouchi (1992)) The general situation investigated in language learning can be described as follows: Given more and more eventually incomplete information concerning the language to be learned, the inference device has to produce, from time to time, a hypothesis about the phenomenon to be inferred. The set of ....

[Article contains additional citation context not shown here]

Mukouchi, Y. (1992), Inductive inference with bounded mind changes, in "Proceedings 3rd Workshop on Algorithmic Learning Theory," October 1992, Tokyo, Japan, JSAI, pp. 125 - 134.

....from positive data that avoids overgeneralization. Finally, language learning with a bounded number of mind changes is completely characterized in terms of recursively generable finite sets. These characterizations offer a new method to handle overgeneralizations and resolve an open question of Mukouchi (1992). 1. Introduction Inductive inference is the process of hypothesizing a general rule from eventually incomplete data. Within the last three decades it received much attention from computer scientists. Nowadays inductive inference can be considered as a form of machine learning with potential ....

....1988, Fulk, 1990) Looking at potential applications it seemed reasonable to restrict ourselves to study language learning of families of uniformly recursive languages. Recently, this topic has attracted much attention (cf. e.g. Shinohara, 1990, Kapur and Bilardi, 1992, Lange and Zeugmann, 1992, Mukouchi, 1992). The general situation investigated in language learning can be described as follows: Given more and more information concerning the language to be learnt, the inference device has to produce, from time to time, a hypothesis about the phenomenon to be inferred. The set of all admissible ....

[Article contains additional citation context not shown here]

Mukouchi, Y. (1992), Inductive Inference with Bounded Mind Changes, in Proc. "Algorithmic Learning Theory," October 1992, Tokyo, Japan, JSAI.

....from positive data that avoids overgeneralization. Finally, language learning with a bounded number of mind changes is completely characterized in terms of recursively generable finite sets. These characterizations offer a new method to handle overgeneralizations and resolve an open question of Mukouchi (1992). 1. Introduction Inductive inference is the process of hypothesizing a general rule from eventually incomplete data. It has its historical origins in the philosophy of science. However, within the last three decades it received much attention from computer scientists. Nowadays inductive ....

....families of uniformly recursive languages. Recently, this topic has attracted much attention (cf. e.g. Shinohara (1990) Kapur and Bilardi (1992) 3 This research has been supported by the German Ministry for Research and Technology (BMFT) under grant no. 01 IW 101. Lange and Zeugmann (1992) Mukouchi (1992)) The general situation investigated in language learning can be described as follows: Given more and more eventually incomplete information concerning the language to be learnt, the inference device has to produce, from time to time, a hypothesis about the phenomenon to be inferred. The set of ....

[Article contains additional citation context not shown here]

Mukouchi, Y. (1992), Inductive Inference with Bounded Mind Changes, to appear in Proceedings "Algorithmic Learning Theory," October 1992, Tokyo, Japan, and Research Institute of Fundamental Information Science, Kyushu University 33, Fukuoka, May 14, 1992, RIFIS-TR-CS-58.

....applications, Angluin (1980) started the systematic study of learning enumerable families of uniformly recursive languages, henceforth called indexed families. Recently, this topic has attracted much attention (cf. e.g. Shinohara (1990) Kapur and Bilardi (1992) Lange and Zeugmann (1993a) Mukouchi (1992), Wiehagen and Zeugmann (1994) Next we specify the information from which the target languages have to be learned. Throughout this paper we exclusively consider learning from positive data, or synonymously from text. A text of a language L is an infinite sequence of strings that eventually ....

....However, all the mentioned papers considered the learnability of recursive functions. Hence, it is only natural to ask whether or not this measure of efficiency is of equal importance in the setting of language learning. This is indeed the case as recently obtained results show (cf. e.g. Mukouchi (1992), Lange and Zeugmann (1993b) Lange (1994) In this paper we study problems of higher granularity. In order to explain them we have to describe the monotonicity constraints we are going to deal with. The three notions of monotonicity reflect different formalizations of the requirement that the ....

Mukouchi, Y. (1992), Inductive inference with bounded mind changes, in "Proceedings 3rd Workshop on Algorithmic Learning Theory," Tokyo, Japan, JSAI, pp. 125 -- 134.

....of the hypothesis space. Obviously, the hypothesis space must contain at least one description for each target language. Hence, we might be tempted to take the indexed family itself as hypothesis space. And indeed, most authors did (cf. e.g. Angluin (1980a, 1980b) Shinohara (1982) Jantke (1991b) Mukouchi (1992)) Moreover, looking at potential applications of a learning system, users of such a system might even be highly interested in getting as hypotheses just the descriptions they proposed. That means they might formulate their learning problems just by specifying a particular indexed family. If an ....

.... has been introduced by Barzdin and Freivalds (1972) Subsequently, various authors used the number of mind changes to characterize the complexity of learning (cf. e.g. Barzdin and Freivalds (1974) Barzdin, Kinber and Podnieks (1974) Case and Smith (1983) Wiehagen, Freivalds and Kinber (1984) Mukouchi (1992, 1994) Gasarch and Velauthapillai (1992) studied active learning in dependence on the number of mind changes. The paper is organized as follows. Section 2 presents preliminaries, i.e. notations and definitions. In Section 3 we exemplify several basic concepts and ideas of language learning. ....

[Article contains additional citation context not shown here]

Mukouchi, Y. (1992), Inductive inference with bounded mind changes, in "Proceedings 3rd Workshop on Algorithmic Learning Theory," October 1992, Tokyo, (S. Doshita, K. Furukawa, K.P. Jantke and T. Nishida, Eds.), Lecture Notes in Artificial Intelligence Vol. 743, pp. 125 -- 134, Springer-Verlag, Berlin.

....a family is learnable with a small memory in one sense and non learnable in a stronger sense. Third, we use the number of mindchanges a learner makes on a text as a measure of learning complexity. Learning with restrictions on the number of mindchanges was widely explored in many works, e.g. in [13, 18]. We found that if some monotonicity requirement A implies B, then any family of languages L which is A inferable with k mindchanges is also B inferable with k mindchanges. On the other hand, if A does not imply B, then there is a family of languages learnable according to A with 2 mind changes ....

Mukouchi, Y. (1992), Inductive inference with bounded mindchanges, in "Proceedings of the 3rd Workshop on Algorithmic Learning Theory", Tokyo, October 1992, JSAI, pp. 125--134.

No context found.

Y. Mukouchi, Inductive inference with bounded mind changes, Proc. 3rd Workshop on Algorithmic Learning Theory (S. Doshita, K. Furukawa, K.P. Jantke and T. Nishida, Eds.), Springer-Verlag, Berlin, 1993, Lecture Notes in Artificial Intelligence 743, pp. 125 -- 134.

No context found.

Mukouchi, Y. (1992b), Inductive inference with bounded mind changes, in "Proceedings 3rd Workshop on Algorithmic Learning Theory," October 1992, Tokyo, JSAI, pp. 125 - 134.

No context found.

Mukouchi, Y. (1992b), Inductive Inference with Bounded Mind Changes, in "Proceedings 3rd Workshop on Algorithmic Learning Theory," October 1992, Tokyo, JSAI, pp. 125 - 134.

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