In this paper, the criterion for evaluating inductive inference is considered from the information theoretical concept, especially from the view points of source coding and decision theory. Although the finite behavior of the inductive inference methods is important in the application field, there is no theoretical criterion for evaluating hypotheses at a finite stage of process. In the previous paper, we have defined an amount of semantic information included in well-formed formulas (wff) and denoted an analogy between inference and source coding. Inductive inference is regarded as source encoding, assuming that observed facts are compressed into a hypothesis similar to the way a source sequence is compressed into a codeword. By using the above definition, we can apply the criterion of source coding especially Minimum Description Length (MDL) to inductive inference. Therefore, the description length for representing a hypothesis is suitable for the criterion for evaluating a hypothesis inference at the finite stage of the inductive inference process. Moreover, by using the relation between the MDL criterion and Bayes risk, inductive inference can be interpreted with Bayes decision theory. The algorithm for the inductive inference of Horn clause is shown as an application of the proposed criterion. In the algorithm, the search space of hypotheses is restricted by using a refinement relation for increasing efficiency.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Toshiyasu MATSUSHIMA, Joe SUZUKI, Hiroshige INAZUMI, Shigeichi HIRASAWA, "Inductive Inference Scheme at a Finite Stage of Process from a View Point of Source Coding" in IEICE TRANSACTIONS on transactions,
vol. E73-E, no. 5, pp. 644-652, May 1990, doi: .
Abstract: In this paper, the criterion for evaluating inductive inference is considered from the information theoretical concept, especially from the view points of source coding and decision theory. Although the finite behavior of the inductive inference methods is important in the application field, there is no theoretical criterion for evaluating hypotheses at a finite stage of process. In the previous paper, we have defined an amount of semantic information included in well-formed formulas (wff) and denoted an analogy between inference and source coding. Inductive inference is regarded as source encoding, assuming that observed facts are compressed into a hypothesis similar to the way a source sequence is compressed into a codeword. By using the above definition, we can apply the criterion of source coding especially Minimum Description Length (MDL) to inductive inference. Therefore, the description length for representing a hypothesis is suitable for the criterion for evaluating a hypothesis inference at the finite stage of the inductive inference process. Moreover, by using the relation between the MDL criterion and Bayes risk, inductive inference can be interpreted with Bayes decision theory. The algorithm for the inductive inference of Horn clause is shown as an application of the proposed criterion. In the algorithm, the search space of hypotheses is restricted by using a refinement relation for increasing efficiency.
URL: https://global.ieice.org/en_transactions/transactions/10.1587/e73-e_5_644/_p
Copy
@ARTICLE{e73-e_5_644,
author={Toshiyasu MATSUSHIMA, Joe SUZUKI, Hiroshige INAZUMI, Shigeichi HIRASAWA, },
journal={IEICE TRANSACTIONS on transactions},
title={Inductive Inference Scheme at a Finite Stage of Process from a View Point of Source Coding},
year={1990},
volume={E73-E},
number={5},
pages={644-652},
abstract={In this paper, the criterion for evaluating inductive inference is considered from the information theoretical concept, especially from the view points of source coding and decision theory. Although the finite behavior of the inductive inference methods is important in the application field, there is no theoretical criterion for evaluating hypotheses at a finite stage of process. In the previous paper, we have defined an amount of semantic information included in well-formed formulas (wff) and denoted an analogy between inference and source coding. Inductive inference is regarded as source encoding, assuming that observed facts are compressed into a hypothesis similar to the way a source sequence is compressed into a codeword. By using the above definition, we can apply the criterion of source coding especially Minimum Description Length (MDL) to inductive inference. Therefore, the description length for representing a hypothesis is suitable for the criterion for evaluating a hypothesis inference at the finite stage of the inductive inference process. Moreover, by using the relation between the MDL criterion and Bayes risk, inductive inference can be interpreted with Bayes decision theory. The algorithm for the inductive inference of Horn clause is shown as an application of the proposed criterion. In the algorithm, the search space of hypotheses is restricted by using a refinement relation for increasing efficiency.},
keywords={},
doi={},
ISSN={},
month={May},}
Copy
TY - JOUR
TI - Inductive Inference Scheme at a Finite Stage of Process from a View Point of Source Coding
T2 - IEICE TRANSACTIONS on transactions
SP - 644
EP - 652
AU - Toshiyasu MATSUSHIMA
AU - Joe SUZUKI
AU - Hiroshige INAZUMI
AU - Shigeichi HIRASAWA
PY - 1990
DO -
JO - IEICE TRANSACTIONS on transactions
SN -
VL - E73-E
IS - 5
JA - IEICE TRANSACTIONS on transactions
Y1 - May 1990
AB - In this paper, the criterion for evaluating inductive inference is considered from the information theoretical concept, especially from the view points of source coding and decision theory. Although the finite behavior of the inductive inference methods is important in the application field, there is no theoretical criterion for evaluating hypotheses at a finite stage of process. In the previous paper, we have defined an amount of semantic information included in well-formed formulas (wff) and denoted an analogy between inference and source coding. Inductive inference is regarded as source encoding, assuming that observed facts are compressed into a hypothesis similar to the way a source sequence is compressed into a codeword. By using the above definition, we can apply the criterion of source coding especially Minimum Description Length (MDL) to inductive inference. Therefore, the description length for representing a hypothesis is suitable for the criterion for evaluating a hypothesis inference at the finite stage of the inductive inference process. Moreover, by using the relation between the MDL criterion and Bayes risk, inductive inference can be interpreted with Bayes decision theory. The algorithm for the inductive inference of Horn clause is shown as an application of the proposed criterion. In the algorithm, the search space of hypotheses is restricted by using a refinement relation for increasing efficiency.
ER -