A comparison of identification criteria for inductive inference of recursive real-valued functions

被引:4
|
作者
Hirowatari, E [1 ]
Arikawa, S
机构
[1] Kitakyushu Univ, Ctr Informat Proc Res & Educ, Kitakyushu, Fukuoka 8028577, Japan
[2] Kyushu Univ, Dept Informat, Fukuoka 8128581, Japan
关键词
D O I
10.1016/S0304-3975(00)00275-9
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this paper we investigate the inductive inference of recursive real-valued functions from data. A recursive real-valued function is regarded as a computable interval mapping. The teaming model we consider in this paper is an extension of Gold's inductive inference. We first introduce some criteria for successful inductive inference of recursive real-valued functions. Then we show a recursively enumerable class of recursive real-valued functions which is not inferable in the limit. This should be an interesting contrast to the result by Wiehagen (1976, Elektronische Informations verarbeitung und Kybernetik, Vol. 12, pp. 93-99) that every recursively enumerable subset of recursive functions from N to N is consistently inferable in the limit. We also show that every recursively enumerable class of recursive real-valued functions on a fixed rational interval is consistently inferable in the limit. Furthermore, we show that our consistent inductive inference coincides with the ordinary inductive inference, when we deal with recursive real-valued functions on a fixed closed rational interval. (C) 2001 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:351 / 366
页数:16
相关论文
共 50 条
  • [1] A comparison of identification criteria for inductive inference of recursive real-valued functions
    Hirowatari, E
    Arikawa, S
    ALGORITHMIC LEARNING THEORY, 1998, 1501 : 262 - 275
  • [2] On the inductive inference of recursive real-valued functions
    Apsitis, K
    Arikawa, S
    Freivalds, R
    Hirowatari, E
    Smith, CH
    THEORETICAL COMPUTER SCIENCE, 1999, 219 (1-2) : 3 - 17
  • [3] Criteria for inductive inference with mind changes and anomalies of recursive real-valued functions
    Hirowatari, E
    Hirata, K
    Miyahara, T
    Arikawa, S
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2003, E86D (02) : 219 - 227
  • [4] Inferability of recursive real-valued functions
    Hirowatari, E
    Arikawa, S
    ALGORITHMIC LEARNING THEORY, 1997, 1316 : 18 - 31
  • [5] Recursive characterization of computable real-valued functions and relations
    Brattka, V
    THEORETICAL COMPUTER SCIENCE, 1996, 162 (01) : 45 - 77
  • [6] Recursive characterization of computable real-valued functions and relations
    Fern Universitaet Hagen, Hagen, Germany
    Theor Comput Sci, 1 (45-77):
  • [7] Prediction of recursive real-valued functions from finite examples
    Hirowatari, Eiju
    Hirata, Kouichi
    Miyahara, Tetsuhiro
    NEW FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2006, 4012 : 224 - 234
  • [8] COMPARISON OF IDENTIFICATION CRITERIA FOR MACHINE INDUCTIVE INFERENCE
    CASE, J
    SMITH, C
    THEORETICAL COMPUTER SCIENCE, 1983, 25 (02) : 193 - 220
  • [9] for derivative of real-valued functions
    Magiotto, Murilo H.
    Zanin, Guilherme L.
    Cardoso, Wesley B.
    Avelar, Ardiley T.
    Gomes, Rafael M.
    OPTICS AND LASER TECHNOLOGY, 2025, 182
  • [10] ON OSCILLATIONS OF REAL-VALUED FUNCTIONS
    Kharazishvili, Alexander
    TRANSACTIONS OF A RAZMADZE MATHEMATICAL INSTITUTE, 2021, 175 (01) : 63 - 67