Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
測定に起因するバイアスについて
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Yurika Kawazoe
December 14, 2021
Research
1.9k
1
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
測定に起因するバイアスについて
Yurika Kawazoe
December 14, 2021
More Decks by Yurika Kawazoe
See All by Yurika Kawazoe
Chapter9_MEASUREMENT_BIAS.pdf
yurika_kawazoe
0
84
Moden epidemiology Chap.26 Social Epidemiology
yurika_kawazoe
0
200
Other Decks in Research
See All in Research
Source Code Diff Revolution
tsantalis
0
180
最先端NLP 2026 論文紹介: Wait, Wait, Wait... Why Do Reasoning Models Loop? / SNLP Paper Review: Wait, Wait, Wait... Why Do Reasoning Models Loop?
tkng
0
250
適応的スパムフィルタのための軽量な類似メッセージカウンタ / jsai2026-adaptive-spam-filter
monochromegane
0
5.8k
NLP colloquium: AI Safety Survey
kanekomasahiro
2
1.1k
Physical AIでモデリングはどう変わるか/How Physical AI Will Change Modeling
stktu
0
290
Harness Engineering and Al Agent
kzinmr
3
2k
学術バーQ AI研究最前線:自己教師あり学習による画像モデルの事前学習
naok615
0
140
Anthropic が提案する LLM の内部状態を自然言語で説明可能にした Natural Language Autoencoders / Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations
shunk031
0
320
医療LLMの現在地〜最新研究から社会実装までを考える〜
kento1109
1
1.8k
完全自律LLMエージェントでDIVER OSINT CTF 2026に挑戦してみた
analokmaus
0
750
Evaluation génomique des femelles laitières croisées : comprendre la méthode pour accompagner les éleveurs à son utilisation
institutdelelevage
PRO
0
150
Karkada さんの論文 × 2 の紹介: (1) Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models, (2) Symmetry in language statistics shapes the geometry of model representations
eumesy
PRO
1
820
Featured
See All Featured
Building Adaptive Systems
keathley
44
3.2k
Optimizing for Happiness
mojombo
378
71k
Primal Persuasion: How to Engage the Brain for Learning That Lasts
tmiket
0
490
Large-scale JavaScript Application Architecture
addyosmani
515
110k
The Invisible Side of Design
smashingmag
301
52k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
18k
Documentation Writing (for coders)
carmenintech
77
5.6k
Facilitating Awesome Meetings
lara
57
7.2k
[Rails World 2026] Durable orchestration on Rails: from continuation to workflow
palkan
1
480
DevOps and Value Stream Thinking: Enabling flow, efficiency and business value
helenjbeal
1
400
Making the Leap to Tech Lead
cromwellryan
135
10k
Google's AI Overviews - The New Search
badams
0
1.6k
Transcript
ଌఆʹىҼ͢Δ όΠΞεʹ͍ͭͯ ࡚େֶපӃ ྟচݚڀηϯλʔ ఴඦ߹߳ LBXB[PFZ!OBHBTBLJVBDKQ
ຊͷ༰ n όΠΞεͱʁ n ଌఆޡࠩͱޡྨ n ۩ମྫͱ༧๏ n ใόΠΞεͷӨڹ
̍ ̎ ̏ ̐
ຊͷ༰ n όΠΞεͱʁ n ଌఆޡࠩͱޡྨ n ۩ମྫͱ༧๏ n ใόΠΞεͷӨڹ
̍ ̎ ̏ ̐
όΠΞεͱʁʛݚڀΛߦ͏ཧ༝ Պֶతͳڵຯ ױऀ͞ΜʹΑΓྑ͍ҩྍΛಧ͚ΔͨΊ ֶҐऔಘʹඞཁ ্࢘ʹΔΑ͏ʹݴΘΕͨ ݚڀΛߦ͏ཧ༝ͳΜͰ͔͢ʁ ױऀ͞Μͷ໋Λٹ͏ɾ20-ΛߴΊΔ
όΠΞεͱʁʛΤϏσϯεʹج͍ͮͨҩྍͷఏڙ ױऀ͞ΜʹΑΓྑ͍ҩྍΛಧ͚ΔͨΊʹ ΤϏσϯεʢՊֶతࠜڌʣʹج͍ͮͨҩྍͷఏڙ͕ඞཁ ࣭ͷߴ͍ʢଥੑͷ͋Δʣݚڀͷ࣮ࢪ͕ඞཁ ˠ ͜Ε·Ͱʹ࣮ࢪ͞Εͨଟ͘ͷݚڀͷ݁Ռ͕ੵ͞Εɺߏங͞ΕΔ
όΠΞεͱʁʛଥੑͷ͋Δݚڀͬͯʁ όΠΞεͷͳ͍ݚڀ ͭ·Γʜ ݚڀσβΠϯɺํ๏ɺ࣮ࢪܦա͕దͰɺ ʢฏۉͱͯ͠ʣਅͷ݁Ռʹ͍ۙݚڀ݁ՌΛಘΔ͜ͱ͕Ͱ͖Δݚڀͷ͜ͱ ଥੑͷ͋Δݚڀͬͯʁ όΠΞεΛݮΒ͢ྗ͕ඞཁ ݚڀΛ࣮ࢪ͢Δࡍʹ ݪਖ਼തݪխࢠʢ༁ʣʢʣΞυόϯετੳӸֶQࢀߟ
όΠΞεͱʜޡࠩͷҰ෦ όΠΞεͱʁʛۮવʢϥϯμϜʣޡࠩͱܥ౷ޡࠩ ଌఆ͞Εͨͱਅͷͱͷࠩ ᶃ ۮવޡࠩʢ3BOEPNFSSPSʣ ʹ ਫ਼ີʢ1SFDJTJPOʣ ᶄ ܥ౷ޡࠩʢ4ZTUFNBUJDFSSPSʣ
ʹ ଥੑʢ7BMJEJUZʣ όΠΞε
ۮવʢϥϯμϜʣޡࠩ όΠΞεͱʁʛۮવʢϥϯμϜʣޡࠩͱܥ౷ޡࠩ ܥ౷ޡࠩ ཧతͳঢ়گʹؔΘΒͣۮવ͓͜Δޡࠩ ଌఆثɺଌఆऀɺଌఆڥͳͲʹ͕ͳ͍ σʔλͷऩूํ๏ʹ͕͋ΔͨΊɺ ܥ౷తʹ͓͜Δޡࠩ ଌఆثͷނোɺଌఆऀͷओ؍ɺഎܠใͷภΓ ਅ
ਅ
όΠΞεͱʁʛۮવʢϥϯμϜʣޡࠩͱܥ౷ޡࠩ ଥੑ ਫ਼ີ ܥ౷ޡࠩʹόΠΞε ۮવʢϥϯμϜʣޡࠩ େ େ খ
όΠΞεͱʁʛݚڀͷϑϩʔͱରԠ͢ΔόΠΞε ԾઆόΠΞε ަབྷ બόΠΞε ใόΠΞε ੳόΠΞε ग़൛όΠΞε ղऍόΠΞε ⽊原正博/⽊原雅⼦(訳)(2020).
アドバンスト分析疫学. p124参考 දతͳͷͭ Ծઆ ରूஂ ݚڀࢀՃऀ σʔλऩू ౷ܭղੳ จ ղऍ
όΠΞεͱʁʛදతͳͭͷόΠΞεʢલճͷ͓͞Β͍ʣ ަབྷ બόΠΞεʢ߹ྲྀόΠΞεʣ ҨཁҼ ٤Ԏ ڞ௨ޮՌ ৺ଁප ࢮ ৺Ҡ২
࣬පͷॏ ڞ௨ݪҼ ௐ͠ͳ͍ͱόΠΞε͕ى͜Δ ௐ͢ΔͱόΠΞε͕ى͜Δ ҼՌάϥϑʢ%"(ɿ%JSFDU"DZDMJD(SBQIʣ ʢݪҼʣ ʢ݁Ռʣ ʢݪҼʣ ʢ݁Ռʣ ຊؔ࿈͕ͳ͍ͷʹؔ࿈ͯ͠͠·͏
ଌఆޡࠩͱޡྨʛใόΠΞεͱʁ l ࣬පൃੜͷ༗ແ l എܠใ l മ࿐ l ΞτΧϜ l
ަབྷҼࢠ ଌఆޡࠩʹىҼ͢Δɺݚڀతʢղੳ݁Ռʣʹ༩͑ΔӨڹ ใόΠΞεʢ*OGPSNBUJPO#JBTʣ ݚڀͰ࣮ࢪ͞ΕΔଌఆ શͯʹ͓͍ͯଌఆޡ͕ࠩ ൃੜ͢ΔՄೳੑ͕͋Δ
ຊͷ༰ n όΠΞεͱʁ n ଌఆޡࠩͱޡྨ n ۩ମྫͱ༧๏ n ใόΠΞεͷӨڹ
̍ ̎ ̏ ̐
ଌఆޡࠩʹىҼ͢Δɺݚڀతʢղੳ݁Ռʣʹ༩͑ΔӨڹ ଌఆޡࠩͱޡྨʛଌఆޡࠩͱʁ ใόΠΞε ଌఆޡࠩ .FBTVSFNFOUFSSPS ଌఆ͍ͨ͠ͷͷਅͱଌఆͷͣΕʢܥ౷ޡࠩʣ
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢ̍ʣߏ֓೦ͷଥੑ ݄ Ր ਫ ۚ ݄
Ր ਫ ۚ "͞Μ #͞Μ ݄ Ր ਫ ۚ $͞Μ ഋ ഋ ഋ
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢ̍ʣߏ֓೦ͷଥੑ ʮ̍िؒͷ͏ͪ̍ʹഋҎ্ͷΞϧίʔϧΛҿΜͩʯ Ξϧίʔϧઁऔྔ ؊ߗมൃੜͷ༗ແ മ࿐ ΞτΧϜ മ࿐ͷఆ͕ٛݚڀతʹෆҰக ʮ̍िؒͷ͏ͪʹҿΜͩΞϧίʔϧͷྔʯ ͞Βʹ໌֬ʹ͢ΔͨΊʹΞϧίʔϧʜ
ྫʣΞϧίʔϧઁऔྔͱ؊ߗมൃੜͱͷؔ࿈ΛධՁ͍ͨ͠
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢ̍ʣߏ֓೦ͷଥੑ ߏ֓೦ͷଥੑ ଌఆ͍ͨ͠ͷͱଌఆ͞Εͨͷͷ֓೦͕ͲΕ͘Β͍ରԠ͍ͯ͠Δ͔ ݚڀܭըஈ֊Ͱݚڀͷతʹ߹ͬͨമ࿐ͷఆٛΛेʹݕ౼͢Δ
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷऩू ̎σʔλͷऩू هԱهɺใࠂͷޡΓ
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷऩू σʔλͷऩूํ๏ n ௐࠪථʢ༣ศɺిɺ8&#ɺ໘ʣ n هʢҩྍهௐࠪɺ৬ۀهௐࠪʣ n ొʢߦ͕ཧ͢Δ݈߁هɺਓޱಈଶɺ͕Μొʣ Ͳͷ߹Ͱଌఆޡࠩى͜Δ
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷऩू ௐࠪථʢ༣ศɺిɺ8&#ɺ໘ʣ ݄ Ր ਫ ۚ
ݚڀରऀͷهԱʹཔΔௐࠪථͷճ هԱ͕͔֬Ͱͳ͍߹ޡͬͨճ 2 ̍िؒͷ͏ͪʹҿΜͩΞϧίʔϧͷྔʁ
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷऩू هʢҩྍهௐࠪɺ৬ۀهௐࠪʣ ిࢠΧϧςʹೖྗͷޡΓ͕͋Δ ه͕͔֬Ͱͳ͍߹ޡͬͨσʔλ
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷऩू ొʢߦ͕ཧ͢Δ݈߁هɺਓޱಈଶɺ͕Μొʣ ఏڙ͞Εͨσʔλͷ࣭͕ѱ͍ ొ͞Εͨσʔλͷ࣭ѱ͍ ఏڙ ɾॲํ༰ͷొ͕ શͰͳ͍ ɾసؼͷະొ FUD
ొ நग़
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷऩू ̎σʔλͷऩू هԱهɺใࠂͷޡΓ σʔλͷޡΓආ͚ΒΕͳ͍ σʔλʹޡΓ͕͋ΔՄೳੑΛҙ͓ࣝͯ͘͜͠ͱ͕େࣄ
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷཧͱऔΓѻ͍ σʔλͷཧͱऔΓѻ͍ σʔλͷҠɺม࣌ͷૢ࡞ϛε
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷऩू σʔλͷҠ .*44 .*44 ݪࢿྉʢ࣭ථධՁγʔτʣ͔Βͷೖྗϛε ݪࢿྉ ղੳ༻σʔληοτ ೖྗ μϒϧΤϯτϦʔϞχλϦϯάͰճආՄೳ
.*44
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷऩू σʔλͷม ྸΛऩू͍ͨ͠ ੜ݄Λऩू͠ྸΛखܭࢉ ܭࢉϛε
ଌఆޡࠩͱޡྨʛଌఆޡ͕ࠩى͜ΔݪҼʢʣσʔλͷऩू σʔλͷม ࠷جૅͱͳΔσʔλΛऩू͠ɺίϯϐϡʔλΛͬͯม͢Δ ੜ݄Λऩू͠ɺ ίϯϐϡʔλͰඞཁͳ࣌ͷྸΛࢉग़͢Δํ͕ਖ਼֬
ଌఆޡࠩͱޡྨʛଌఆޡࠩͱޡྨ ࿈ଓม ʢɺମॏɺݕࠪʣ ଌఆޡࠩ .FBTVSFNFOUFSSPS ࢄม ʢੑผɺ٤Ԏͷ༗ແʣ ޡྨʢྨޡࠩʣ .JTDMBTTJGJDBUJPO
ଌఆޡࠩ .FBTVSFNFOUFSSPS ଌఆ͢ΔมͷܕʹΑͬͯݺͼํ͕ҟͳΔ ؆୯ͷͨΊࢄมͰ͓͠͠·͢
ଌఆޡࠩͱޡྨʛޡྨ̐छྨ • ಠཱඇࠩҟʢ*OEFQFOEFODFOPOEJGGFSFOUJBMʣ • ಠཱࠩҟʢ*OEFQFOEFODFEJGGFSFOUJBMʣ • ैଐඇࠩҟʢ%FQFOEFODFOPOEJGGFSFOUJBMʣ • ैଐࠩҟʢ%FQFOEFODFEJGGFSFOUJBMʣ
ಠཱੑͱࠩҟੑͷΈ߹ΘͤʹΑΓ ࣍ͷͭͷλΠϓʹྨͰ͖Δ
ଌఆޡࠩͱޡྨʛ%"(Λͬͨޡྨͷઆ໌ ҼՌάϥϑʢ%"(ɿ%JSFDU"DZDMJD(SBQIʣ " ελνϯͷ༻ : ΞτΧϜ ˞؆୯ͷͨΊަབྷબόΠΞεͳ͍ઃఆ " :
ଌఆޡࠩͱޡྨʛ %"(Λͬͨޡྨͷઆ໌ ҼՌάϥϑʢ%"(ɿ%JSFDU"DZDMJD(SBQIʣ " ελνϯͷ༻ : ΞτΧϜ " :
ਅͷ ˞؆୯ͷͨΊަབྷબόΠΞεͳ͍ઃఆ
ଌఆޡࠩͱޡྨʛҼՌάϥϑɿଌఆ͞Εͨ "ˎͱ:ˎ " ελνϯͷ༻ : ΞτΧϜ " Χϧς͔Βऩूͨ͠ελνϯͷ༻ :
ɿΧϧς͔Βऩूͨ͠ΞτΧϜ ଌఆ͞Εͨ "ˎͱ:ˎ :ˎ " "ˎ :
ଌఆޡࠩͱޡྨʛҼՌάϥϑɿଌఆޡࠩ 6" ͱ6: ଌఆޡࠩ 6" ͱ6: :ˎ 6" "
"ˎ : 6: " ελνϯͷ༻ : ΞτΧϜ " Χϧς͔Βऩूͨ͠ελνϯͷ༻ : ɿΧϧς͔Βऩूͨ͠ΞτΧϜ 6" " ͷΛܾఆ͢Δ"Ҏ֎ͷͯ͢ͷཁҼ 6: ɿ: ͷΛܾఆ͢Δ:Ҏ֎ͷͯ͢ͷཁҼ
ଌఆޡࠩͱޡྨʛҼՌάϥϑɿղੳʹ༻͍Δͷ "ˎͱ:ˎ ղੳʹ͏σʔλɺਅͷॲஔ "Ͱͳ͘ଌఆ͞Εͨॲஔ " ਅͷΞτΧϜ :Ͱͳ͘ଌఆ͞ΕͨΞτΧϜ :
:ˎ 6" " "ˎ : 6: " ελνϯͷ༻ : ΞτΧϜ " Χϧς͔Βऩूͨ͠ελνϯͷ༻ : ɿΧϧς͔Βऩूͨ͠ΞτΧϜ 6" " ͷΛܾఆ͢Δ"Ҏ֎ͷͯ͢ͷཁҼ 6: ɿ: ͷΛܾఆ͢Δ:Ҏ֎ͷͯ͢ͷཁҼ
ଌఆޡࠩͱޡྨʛޡྨ̐छྨɿಠཱੑ "ɿༀͷ༻ :ɿ؊ಟੑ " ɿΧϧς͔Βऩूͨ͠ༀͷ༻ : ɿΧϧς͔Βऩूͨ͠؊ಟੑ 6" ɾ6:
ɿΧϧςͷೖྗϛε :ˎ 6" " "ˎ : 6: ྫʣ"ͱ :ͲͪΒΧϧς͔Βऩूͨ͠߹ ಠཱޡྨ ʹ 6" ͱ 6: ͕ಠཱ
ଌఆޡࠩͱޡྨʛޡྨ̐छྨɿಠཱੑ ैଐʢґଘʣޡྨ ʹ 6" ͱ 6: ͕ґଘ "ɿༀͷ༻ :ɿ؊ಟੑ
" ɿΠϯλϏϡʔͰऩूͨ͠ༀͷ༻ : ɿΠϯλϏϡʔͰऩूͨ͠؊ಟੑ 6" ɾ6: ɿױऀ͞ΜͷهԱ 6":ɿ ױऀ͞Μͷࢥ͍ग़͢ೳྗ ྫʣ"ͱ :ͷͲͪΒױऀ͞ΜͷిΠϯλϏϡʔͰऩूͨ͠߹ :ˎ 6" " "ˎ : 6: 6":
ଌఆޡࠩͱޡྨʛޡྨ̐छྨɿࠩҟੑ ࠩҟޡྨ ʹ "͕ :ͷଌఆʹӨڹΛ༩͑Δʢٯಉ͡ʣ "ɿༀͷ༻ :ɿ؊ಟੑ " ɿΧϧς͔Βऩूͨ͠ༀͷ༻
: ɿΧϧς͔Βऩूͨ͠؊ಟੑ 6" ɾ6: ɿΧϧςͷೖྗϛε :ˎ 6" " "ˎ : 6: ྫʣ"ͷༀΛ͏ͱ؊ಟੑΛى͜͢ͱٙ͏ҩࢣ͕ "ͷༀΛ༩͞Εͨױऀ͞ΜΛଞͷױऀ͞ΜΑΓҙਂ͘؍͢Δ
ଌఆޡࠩͱޡྨʛޡྨ̐छྨɿࠩҟੑ ඇࠩҟޡྨ "͕ :ʹӨڹΛ༩͑ͳ͍ʢٯಉ͡ʣ "ɿༀͷ༻ :ɿ؊ಟੑ " ɿΧϧς͔Βऩूͨ͠ༀͷ༻ :
ɿΧϧς͔Βऩूͨ͠؊ಟੑ 6" ɾ6: ɿΧϧςͷೖྗϛε :ˎ 6" " "ˎ : 6: ྫʣ"ͱ :ͲͪΒΧϧς͔Βऩूͨ͠߹ʢಠཱޡࠩͱಉ͡ʣ
ଌఆޡࠩͱޡྨʛޡྨ̐छྨ :ˎ 6" " "ˎ : 6: :ˎ 6"
" "ˎ : 6: :ˎ 6" " "ˎ : 6: :ˎ 6" " "ˎ : 6: 6": :ˎ 6" " "ˎ : 6: 6": :ˎ 6" " "ˎ : 6: 6": ಠཱඇࠩҟ ैଐඇࠩҟ ಠཱࠩҟ ैଐࠩҟ
ຊͷ༰ n όΠΞεͱʁ n ଌఆޡࠩͱޡྨ n ۩ମྫͱ༧๏ n ใόΠΞεͷӨڹ
̍ ̎ ̏ ̐
۩ମྫͱ༧๏ʛ മ࿐ͷଌఆʹؔ͢ΔόΠΞε l ىόΠΞεʢϦίʔϧόΠΞεʣ l ໘ऀόΠΞε ΞτΧϜͷଌఆʹؔ͢ΔόΠΞε l ؍ऀόΠΞε l
ԠόΠΞε
۩ମྫͱ༧๏ʛىόΠΞεʢϦίʔϧόΠΞεʣ ىόΠΞεʢϦίʔϧόΠΞεʣ മ࿐ͷଌఆΛݚڀରऀͷهԱʹཔΔ߹ʹى͜Γ͍͢ έʔείϯτϩʔϧݚڀͰى͜Γ͍͢
۩ମྫͱ༧๏ʛىόΠΞεʢϦίʔϧόΠΞεʣ ྫʣༀͷ༻͕ೝͷൃʹؔ࿈͢Δ͔ΛධՁ͍ͨ͠ ೝͷױऀ͞Μʹༀͷ༻ʹ͍ͭͯௐࠪ͢Δ :ˎ 6" " "ˎ : 6:
ೝɺༀͷ༻Λࢥ͍ग़͢͜ͱʹӨڹΛ༩͑Δ ΞτΧϜʹΑͬͯമ࿐ʹର͢ΔهԱͷΓํ͕ҧͬͯ͠·͏ ಠཱࠩҟ "ɿༀͷ༻ "ˎɿฉ͖औΓʹΑΔༀͷ༻ 6" ɿױऀ͞ΜͷهԱ :ɿೝ
۩ମྫͱ༧๏ʛىόΠΞεʢϦίʔϧόΠΞεʣ ྫʣ৷தͷΞϧίʔϧઁऔྔ͕ࣇͷઌఱੑܽଛͷൃʹؔ࿈͢Δ͔ධՁ ग़࢈ޙʹ৷தͷΞϧίʔϧઁऔྔΛ֬ೝͨ͠߹ :ˎ 6" " "ˎ : 6:
ग़࢈ͨ͠ࢠͲ͕ઌఱੑܽଛͰ͋Δ͔Ͳ͏͔͕ɺΞϧίʔϧઁऔྔͷىʹӨڹΛ༩͑Δ ΞτΧϜʹΑ࣮ͬͯࡍʹͳ͔ͬͨമ࿐Λ͋Δͱࢥ͍ࠐΜͰ͠·͏ "ɿ৷தͷΞϧίʔϧઁऔྔ "ˎɿฉ͖औΓʹΑΔΞϧίʔϧઁऔྔ 6" ɿͷهԱ :ɿࣇͷઌఱੑܽଛͷ༗ແ ಠཱࠩҟ
۩ମྫͱ༧๏ʛىόΠΞεʢϦίʔϧόΠΞεʣͷ༧ํ๏ ىόΠΞεͷ༧ํ๏ • ผͷํ๏ʹΑΓରऀͷճͷ֬ূΛಘΔ ྫ̍ʣͷ߹ༀͷ༻ΛΧϧςॲํᝦΑΓ֬ೝ͢Δ • മ࿐ͷධՁʹ٬؍తࢦඪΛ༻͍Δ ҨϚʔΧʔɺੜֶతࢦඪΛ༻͍Δɻ ͨͩ͠ɺݱ࣌ۙͷঢ়ଶΛө͢Δͷ͕ଟ͘༻ʹҙ͕ඞཁ
۩ମྫͱ༧๏ʛ໘ऀόΠΞε ໘ऀόΠΞε ໘ऀ͕έʔε͔ίϯτϩʔϧͰ͋Δ͔Λ͍ͬͯΔͨΊʹ ରԠ͕ภͬͯ͠·͏߹ʹى͜Δ
۩ମྫͱ༧๏ʛ໘ऀόΠΞε ྫʣέʔεɾίϯτϩʔϧݚڀʹ͓͚Δമ࿐ͱΞτΧϜͷؔ࿈ΛධՁ ໘ऀ͕ݚڀରऀͷമ࿐ঢ়گΛ࣭ථʹΑΓଌఆ͢Δ ݚڀରऀͷമ࿐ͷఔͷճʹӨڹΛ༩͑Δ ΞτΧϜʢέʔε͔ίϯτϩʔϧ͔ʣʹΑͬͯ ໘ऀͷݚڀରऀʹର͢ΔରԠ͕ҧͬͯ͠·͏ "ɿമ࿐ "ˎɿ࣭ථʹΑΔമ࿐ͷଌఆ 6"
ɿ໘ऀͷରԠɾઆ໌ :ɿέʔε PSίϯτϩʔϧ :ˎ 6" " "ˎ : 6: ಠཱࠩҟ ʢ࣬ױʣ ʢඇ࣬ױʣ
۩ମྫͱ༧๏ʛ໘ऀόΠΞεͷ༧ํ๏ ໘ऀόΠΞεͷ༧ํ๏ • ৄࡉͳϚχϡΞϧͷ࡞ • ໘ऀͷτϨʔχϯά • σʔλऩू๏ͷඪ४Խ •
σʔλऩूͷϞχλϦϯά • ༧උςετ • ໘ऀͷݕԽ
۩ମྫͱ༧๏ʛ؍ऀόΠΞε ؍ऀόΠΞε ؍ऀ͕മ࿐͔ඇമ࿐Ͱ͋Δ͔Λ͍ͬͯΔͨΊʹ ΞτΧϜͷධՁ͕ภͬͯ͠·͏߹ʹى͜Δ
۩ମྫͱ༧๏ʛ؍ऀόΠΞε ྫʣΞϧίʔϧґଘͱΞϧίʔϧੑ؊ߗมͱͷؔ࿈ΛධՁ ؍ऀ͕ݚڀରऀ͕Ξϧίʔϧੑ؊ߗมͰ͋Δ͔පཧஅʹΑΓఆ͢Δ മ࿐͔ඇമ࿐͔ʹΑͬͯ؍ऀͷපཧஅʹӨڹΛ༩͑ɺ පཧஅͷ݁Ռ͕ภͬͯ͠·͏ "ɿΞϧίʔϧґଘ 6: ɿ؍ऀͷපཧஅ :ˎɿΞϧίʔϧੑ؊ߗมͷஅ݁Ռ
:ɿΞϧίʔϧੑ؊ߗม ಠཱࠩҟ :ˎ 6" " "ˎ : 6:
۩ମྫͱ༧๏ʛ؍ऀόΠΞεͷ༧ํ๏ ؍ऀόΠΞεͷ༧ํ๏ • ؍ऀͷݕԽ ࠔͳ߹ɺΞτΧϜͷॏʹΑΓผԽͯؒ͠Ͱമ࿐ͷϨϕϧΛ ൺֱ͢Δ͜ͱͰ؍ऀόΠΞεΛධՁ͢Δ͜ͱ͕Ͱ͖Δ ΞτΧϜͷॏ͕͍Ͱമ࿐ͱͷ૬͕ؔೝΊΒΕͨ߹ɺ ؍όΠΞε͕͋Δ͔͠Εͳ͍
۩ମྫͱ༧๏ʛԠόΠΞε ԠόΠΞε ϑΥϩʔΞοϓظؒதͷΞτΧϜͷධՁΛ ױऀ͞ΜͷࣗݾใࠂʹཔΔ߹Ͱ ٬؍తࢦඪΛ༻͍Δ͜ͱ͕Ͱ͖ͳ͍߹ʹى͜Δ
۩ମྫͱ༧๏ʛԠόΠΞε ྫʣമ࿐ͱϑΥϩʔΞοϓظؒதͷภ಄௧ͷൃੜΛධՁ͢Δ ױऀ͞Μ͕ϑΥϩʔΞοϓظؒதͷภ಄௧ͷൃੜʹ͍ͭͯࣗݾใࠂ͢Δ ࣗݾใࠂʹΑΔଌఆױऀ͞Μͷใࠂͷਖ਼֬ੑʹΑΓճ͕ภͬͯ͠·͏ "ɿമ࿐ 6: ɿױऀ͞Μͷใࠂͷਖ਼֬ੑ :ˎɿଌఆʢࣗݾใࠂʣ͞Εͨภ಄௧ :ɿภ಄௧ͷൃੜ
ಠཱඇࠩҟ :ˎ 6" " "ˎ : 6:
۩ମྫͱ༧๏ʛԠόΠΞε ԠόΠΞεͷ༧ํ๏ ɾؔ࿈͢Δঢ়Λ߹Θͤͯऩू͢Δ ภ಄௧ͷൃੜͷྨΛؔ࿈͢Δࢦඪʢు͖ؾɺർ࿑ײͳͲʣͱͱʹऩू͠ɺ ٬؍తʹධՁ͢Δ ɾઐ༻ͷ࣭ථΛ༻͢Δ ڱ৺ຫੑؾࢧԌɺ͏ͭපͱ͍ͬͨҰ෦ͷঢ়ઐ༻ͷ࣭ථ͕ ։ൃ͞Ε͍ͯΔ
ຊͷ༰ n όΠΞεͱʁ n ଌఆޡࠩͱޡྨ n ۩ମྫͱ༧๏ n ใόΠΞεͷӨڹ
̍ ̎ ̏ ̐
ใόΠΞεͷӨڹʛใόΠΞεͷํ جຊతʹඇࠩҟͷޡྨաখධՁʢ/VMMʹ͔͏όΠΞεʣʹͳΔ ͨͩ͠ɺമ࿐ม͕ • ͭҎ্ͷΧςΰϦ͕͋Δ • ࿈ଓΛΧςΰϥΠζͨ͠มͰ͋Δ • ଞͷมʹґଘͯ͠ൃੜͨ͠ޡྨͰ͋Δʢैଐޡྨʣ
աେධՁʢ/VMM͔ΒΕΔόΠΞεʣʹͳΔՄೳੑ͕͋Δ :ˎ 6" " "ˎ : 6: :ˎ 6" " "ˎ : 6: ࠩҟ ඇࠩҟ /VMMޮՌͳ͠ͷঢ়ଶͷ͜ͱ ϦεΫൺΦοζൺ ϦεΫࠩ ʹ
ޡྨ͕ͳ͍߹ മ࿐ έʔε ίϯτϩʔϧ ͋Γ ͳ͠
֤܈Ͱമ࿐Λड͚ͨਓʑͷˋ͕ඇമ࿐܈ʹ ޡྨ͞Εͨ߹ മ࿐ έʔε ίϯτϩʔϧ ͋Γ r ͳ͠ ใόΠΞεͷӨڹʛέʔείϯτϩʔϧݚڀɿඇࠩҟͷ߹ աখධՁ ʢ/VMMʹ͔͏όΠΞεʣ
աେධՁ ʢ/VMM͔ΒΕΔ όΠΞεʣ ޡྨ͕ͳ͍߹ മ࿐ έʔε ίϯτϩʔϧ Φοζൺ
ߴ༻ྔ WTͳ͠ ༻ྔ WTͳ͠ ͳ͠ʢ3FGFSFODFʣ ߴ༻ྔ܈ͷਓͷˋ͕༻ྔ܈ʹޡྨ͞Εͨ߹ മ࿐ έʔε ίϯτϩʔϧ Φοζൺ ߴ༻ྔ WTͳ͠ ༻ྔ WTͳ͠ ͳ͠ʢ3FGFSFODFʣ ใόΠΞεͷӨڹʛέʔείϯτϩʔϧݚڀɿͭҎ্ͷΧςΰϦ
ใόΠΞεͷӨڹʛใόΠΞεͷํ ͪͳΈʹʜ • ࠩҟͷޡྨجຊతʹաେධՁʹͳΔʢ/VMM͔ΒΕΔόΠΞεʣ • ޡྨ͕ҰํͰͳ͍߹ɺଧͪফ͋ͬͨ͠ΓɺաେධՁʹաখ ධՁʹͳΔ͜ͱ͕͋Δ • ަབྷҼࢠͷଌఆͰใόΠΞε͕ൃੜ͢Δͱ͞ΒʹόΠΞεͷํΛ
༧ଌ͢Δ͜ͱ͘͠ͳΔ جຊతʹඇࠩҟͷޡྨաখධՁʢ/VMMʹ͔͏όΠΞεʣʹͳΔ ͨͩ͠ɺമ࿐ม͕ • ͭҎ্ͷΧςΰϦ͕͋Δ • ࿈ଓΛΧςΰϥΠζͨ͠มͰ͋Δ • ଞͷมʹґଘͯ͠ൃੜͨ͠ޡྨͰ͋Δʢैଐޡྨʣ աେධՁʢ/VMM͔ΒΕΔόΠΞεʣʹͳΔՄೳੑ͕͋Δ
ใόΠΞεͷӨڹʛใόΠΞεͷํ ͨͩ͠ɺඇࠩҟʹ͢Δ͜ͱ͕Ͱ͖ͨͱͯ͠ɺׂͷ९कঢ়گ͕ѱ͍߹ɺ աେධՁʢ/VMM͔ΒΕΔόΠΞεʣʹͳΔՄೳੑ͋Δ͠ɺ શମͱͯ͠ͷόΠΞεΛେ͖͘͢ΔՄೳੑ͋Δ ࠩҟΑΓඇࠩҟͰ͋Δํ͕خ͍͠ 3$5ʢϥϯμϜԽൺֱࢼݧʣͰͷݕԽ ࠩҟͷޡྨΛඇࠩҟͷޡྨʹ͢Δ͜ͱͰ ݁Ռ͕อकతʢաখධՁʣʹͳΔ͜ͱΛظ͍ͯ͠Δ
ใόΠΞεͷӨڹʛ3$5ʹ͓͚ΔݕԽɿࠩҟΛඇࠩҟ ׂ PVUDPNF ҩࢣͷߦಈม༰ ؍ऀόΠΞε ױऀͷߦಈม༰ ϓϥηϘޮՌ USFBUNFOU ೋॏݕൺֱࢼݧʢ%PVCMFCMJOEUSJBMʣ
ݕԽ ʢ#MJOEʣ " : ׂ PVUDPNF ҩࢣͷߦಈม༰ ؍ऀόΠΞε ױऀͷߦಈม༰ ϓϥηϘޮՌ USFBUNFOU " : :ˎ 6" " "ˎ : 6: :ˎ 6" " "ˎ : 6: ಠཱࠩҟ ಠཱඇࠩҟ
ใόΠΞεͷӨڹʛใόΠΞεͷఔʹ͍ͭͯʢ·ͩษڧதʣ ඇࠩҟͷޡྨɺݕূʹར༻Ͱ͖Δσʔλ͕͋Δ߹ɺ ײɾಛҟΛ༻͍ͯͲͷํʹɾͲΕ͘Β͍ใόΠΞε͕ى͖͍ͯΔ͔ ੳ͢Δ͜ͱ͕Մೳ͕͍ͩ͠ɻ ࠩҟͷޡྨʢىόΠΞεʣෆՄɻ
ใόΠΞεͷӨڹʛରॲ๏ʹ͍ͭͯʢ·ͩษڧதʣ ใόΠΞεͷํͱఔͷධՁΛͱʹ ใόΠΞεΛௐ͢Δํ๏͋Δ͕ෳࡶͰ͍͠ɻ ใόΠΞε͕ى͖ͳ͍Α͏ʹ ݚڀܭըஈ֊Ͱσʔλͷଌఆํ๏ʹ͍ͭͯݕ౼Λʂ
n όΠΞεͱʁ l දతͳͭͷόΠΞεɿަབྷɺબόΠΞεɺใόΠΞε n ଌఆޡࠩͱޡྨ l ଌఆޡࠩͷݪҼஈ֊ɿߏ֓೦ͷଥੑɺσʔλͷऩूɺσʔλͷཧͱऔΓѻ͍ l ޡྨछྨ
n ۩ମྫͱ༧๏ n ใόΠΞεͷӨڹͱରॲ๏ l ಠཱඇࠩҟͷޡྨجຊతʹաখධՁͱͳΔ͕ɺ݅ʹΑͬͯաେධՁʹͳΔ l ใόΠΞεௐ͕͍ͨ͠Ίɺݚڀܭըஈ֊Ͱଌఆํ๏ʹ͍͔ͭͯͬ͠Γݕ౼Λʂ ̍ ̎ ̏ ̐ ·ͱΊ
ࢀߟจݙ ݪਖ਼തݪխࢠʢ༁ʣʢʣΞυόϯετੳӸֶ.&%4J 5JNPUIZ--BTI 5ZMFS+7BOEFS8FFMF ,FOOFUI+3PUINBO .PEFSO&QJEFNJPMPHZUI&EJUJPO
)FSOÂO ." 3PCJOT+. $BVTBM*OGFSFODF8IBU*G
͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠