Conventional learning algorithms are considered to be a sort of estimation of the true recognition function from sample patterns. Such an estimation requires a good assumption on a prior distribution underlying behind learning data. On the other hand the human being sounds to be able to acquire a better result from an extremely small number of samples. This forces us to think that the human being might use a
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
Eri YAMAGISHI, Minako NOZAWA, Yoshinori UESAKA, "On the Human Being Presupposition Used in Learning" in IEICE TRANSACTIONS on Fundamentals,
vol. E79-A, no. 10, pp. 1601-1607, October 1996, doi: .
Abstract: Conventional learning algorithms are considered to be a sort of estimation of the true recognition function from sample patterns. Such an estimation requires a good assumption on a prior distribution underlying behind learning data. On the other hand the human being sounds to be able to acquire a better result from an extremely small number of samples. This forces us to think that the human being might use a
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e79-a_10_1601/_p
Copy
@ARTICLE{e79-a_10_1601,
author={Eri YAMAGISHI, Minako NOZAWA, Yoshinori UESAKA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={On the Human Being Presupposition Used in Learning},
year={1996},
volume={E79-A},
number={10},
pages={1601-1607},
abstract={Conventional learning algorithms are considered to be a sort of estimation of the true recognition function from sample patterns. Such an estimation requires a good assumption on a prior distribution underlying behind learning data. On the other hand the human being sounds to be able to acquire a better result from an extremely small number of samples. This forces us to think that the human being might use a
keywords={},
doi={},
ISSN={},
month={October},}
Copy
TY - JOUR
TI - On the Human Being Presupposition Used in Learning
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1601
EP - 1607
AU - Eri YAMAGISHI
AU - Minako NOZAWA
AU - Yoshinori UESAKA
PY - 1996
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E79-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 1996
AB - Conventional learning algorithms are considered to be a sort of estimation of the true recognition function from sample patterns. Such an estimation requires a good assumption on a prior distribution underlying behind learning data. On the other hand the human being sounds to be able to acquire a better result from an extremely small number of samples. This forces us to think that the human being might use a
ER -