翻訳と辞書 Words near each other ・ Simkin ・ Simkin de Pio ・ Simkins ・ Similan Islands ・ Similar fact evidence ・ Similar Skin ・ Similaria ・ Similarities (album) ・ Similarities between Wiener and LMS ・ Similarity ・ Similarity (geometry) ・ Similarity (network science) ・ Similarity (psychology) ・ Similarity heuristic ・ Similarity invariance ・ Similarity learning ・ Similarity matrix ・ Similarity measure ・ Similarity relation (music) ・ Similarity score ・ Similarity search ・ Similarity solution ・ Similarity transformation ・ SimilarWeb ・ Similaun ・ SIMILE ・ Simile ・ Simile (computer virus) ・ Simile (disambiguation) ・ Simile, Mpumalanga 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 Similarity learning ： ウィキペディア英語版 Similarity learning Similarity learning is an area of supervised machine learning in artificial intelligence. It is closely related to regression and classification, but the goal is to learn from examples a similarity function that measures how similar or related two objects are. It has applications in ranking, in recommendation systems and face verification. == Learning setup == There are three common setups for similarity and metric distance learning. * ''Regression similarity learning''. In this setup, pairs of objects are given $(x\_i^1,\; x\_i^2)$ together with a measure of their similarity $y\_i\; \backslash in\; R$. The goal is to learn a function that approximates $f(x\_i^1,\; x\_i^2)\; \backslash sim\; y\_i$ for every new labeled triplet example $(x\_i^1,\; x\_i^2,\; y\_i)$. This is typically achieved by minimizing a regularized loss $min\_W\; \backslash sum\_i\; loss(w;x\_i^1,\; x\_i^2,y\_i)\; +\; reg(w)$. * ''Classification similarity learning''. Given are pairs of similar objects $(x\_i,\; x\_i^+)$ and non similar objects $(x\_i,\; x\_i^-)$. An equivalent formulation is that every pair $(x\_i^1,\; x\_i^2)$ is given together with a binary label $y\_i\; \backslash in\; \backslash$ that determines if the two objects are similar or not. The goal is again to learn a classifier that can decide if a new pair of objects is similar or not. * ''Ranking similarity learning''. Given are triplets of objects $(x\_i,\; x\_i^+,\; x\_i^-)$ whose relative similarity obey a predefined order: $x\_i$ is known to be more similar to $x\_i^+$ than to $x\_i^-$. The goal is to learn a function $f$ such that for any new triplet of objects $(x,\; x^+,\; x^-)$, it obeys $f(x,\; x^+)\; >\; f(x,\; x^-)$. This setup assumes a weaker form of supervision than in regression, because instead of providing an exact measure of similarity, one only has to provide the relative order of similarity. For this reason, ranking-based similarity learning is easier to apply in real large scale applications. A common approach for learning similarity, is to model the similarity function as a bilinear form. For example, in the case of ranking similarity learning, one aims to learn a matrix W that parametrizes the similarity function $f\_W(x,\; z)\; =\; x^T\; W\; z$. 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「Similarity 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.