翻訳と辞書 Words near each other ・ Ocaña, Spain ・ OCB ・ OCB mode ・ OCBC ・ OCBC Centre ・ OCBC Cycle Singapore ・ OCBC Singapore Continental Cycling Team ・ OCBC Wing Hang Bank ・ OCC ・ OCC Transport ・ OCCA ・ Occacaris ・ Occagnes ・ OCCAID ・ Occam (programming language) ・ Occam learning ・ Occam process ・ Occam's razor ・ Occam-π ・ Occaneechi ・ Occaneechi Band of the Saponi Nation ・ Occasion ・ Occasion for Loving ・ Occasion of sin ・ Occasional Coarse Language ・ Occasional Conformity Act 1711 ・ Occasional Discourse on the Negro Question ・ Occasional furniture ・ Occasional hearing ・ Occasional Oratorio Dictionary Lists mini英和辞書 mini和英辞書 Webster 1913 Latin-English FOLDOC Wikipedia English ウィキペディア

翻訳と辞書　辞書検索 [ 開発暫定版 ] スポンサード リンク Occam learning ： ウィキペディア英語版 Occam learning In Occam Learning, named after Occam's razor, a probably approximately correct (PAC) learning algorithm is evaluated based on its succinctness and performance on the training set, rather than directly on its predictive power on a test set. Occam learnability is equivalent to PAC learnability. ==Definitions of Occam learning and succinctness== The succinctness of a concept $c$ in concept class $C$ can be expressed by the length $size(c)$ of the shortest bit string that can represent $c$ in $C$. Occam learning connects the succinctness of a learning algorithm's output to its predictive power on unseen data. Let $C$ and $H$ be concept classes containing target concepts and hypotheses respectively and let sample set $S$ contain $m$ samples each containing $n$ bits. Then, for constants $\backslash alpha\; \backslash ge\; 0$ and , a learning algorithm $L$ is an (α,β)-Occam algorithm for $C$ using $H$ if, given $S$ labeled according to $c\; \backslash in\; C$, $L$ outputs a hypothesis $h\; \backslash in\; H$ such that $h$ is consistent with $c$ on $S$ (that is, $h(x)=c(x),\backslash forall\; x\; \backslash in\; S$) and $size(h)\; \backslash le\; (n\; \backslash cdot\; size(c))^\backslash alpha\; m^\backslash beta$.〔Kearns, M. J., & Vazirani, U. V. (1994). An introduction to computational learning theory, chapter 2. MIT press.〕〔Blumer, A., Ehrenfeucht, A., Haussler, D., & Warmuth, M. K. (1987). ''(Occam's razor )''. Information processing letters, 24(6), 377-380.〕 Such an algorithm $L$ is called an efficient (α,β)-Occam algorithm if it runs in time polynomial in $n$, $m$, and $size(c)$. 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「Occam learning」の詳細全文を読む スポンサード リンク 翻訳と辞書 : 翻訳のためのインターネットリソース Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.