Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
[読み会] Learning Representations by Humans, for H...
Search
mei28
April 19, 2022
0
35
[読み会] Learning Representations by Humans, for Humans
読み会資料
Learning Representations by Humans, for Humans(ICML2021)
mei28
April 19, 2022
Tweet
Share
More Decks by mei28
See All by mei28
[読み会] CHI2025論文紹介
mei28
1
34
[読み会] “Are You Really Sure?” Understanding the Effects of Human Self-Confidence Calibration in AI-Assisted Decision Making
mei28
0
130
[JSAI'24] 人間の判断根拠は文脈によって異なるのか?〜信頼されるXAIに向けた人間の判断根拠理解〜
mei28
2
710
[CHI'24] Fair Machine Guidance to Enhance Fair Decision Making in Biased People
mei28
0
92
[DEIM2024] 卓球の得点予測における重要要素の分析
mei28
0
55
[Human-AI Decision Making勉強会] 意思決定 with AIは個人vsグループで変わるの?
mei28
0
240
[読み会] Words are All You Need? Language as an Approximation for Human Similality Judgements
mei28
0
57
[参加報告] AAAI'23
mei28
0
120
[計算機構論] Learning Models of Individual Behavior in Chess
mei28
0
96
Featured
See All Featured
The Illustrated Children's Guide to Kubernetes
chrisshort
49
51k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
116
20k
How to train your dragon (web standard)
notwaldorf
97
6.3k
Large-scale JavaScript Application Architecture
addyosmani
514
110k
How to Think Like a Performance Engineer
csswizardry
27
2.1k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
35
3.2k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
30
2.9k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.5k
Side Projects
sachag
455
43k
For a Future-Friendly Web
brad_frost
180
10k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
10
890
Transcript
ൃදऀɿ༶໌ ݄!ಡΈձ -FBSOJOH3FQSFTFOUBUJPOT CZ)VNBOT GPS)VNBOT
จใͱબΜͩཧ༝ બཧ༝ • ਓؒʹରͯ͠ใٕज़Ͱ࡞༻ʢհೖʣʹ͍ͭͯΔͨΊ • )VNBOJOUIFMPPQܥͷจ
ߩݙɿਓؒΛհͯ͠ਓؒʹ༗ӹͳදݱΛ֫ಘՄೳʹ എܠɿػցֶश͕ൃల͖ͯͯ͠ɼҙࢥܾఆʹΘΕ͖͍ͯΔ ɿ҆શੑɼެฏੑͳͲΛߟྀ͢ΔࡍʹӏವΈʹͣ͠Β͍ ఏҊɿਓ͕ؒཧղՄೳͳํ๏ͰใΛఏࣔ͠ɼ ਓؒͷ࠷ऴܾఆΛࢧԉ͢ΔϑϨʔϜϫʔΫ.P.ΛఏҊ ݁ՌɿͭͷλεΫΛ࣮ࢪɽ ਓؒͷҙࢥܾఆʹର্ͯͤ͠͞Δ͜ͱΛࣔͨ͠
͍··Ͱͷҙࢥܾఆࢧԉɿग़ྗΛӏವΈ͠ͳ͍ ػցͷग़ྗ Λਓ͕ؒड͚औΓɼߦಈ ΛͱΔ ̂ y a fθ ̂
y x a
͍··Ͱͷख๏ɿΑ͍ग़ྗΛֶशʢ܇࿅࣌ʣ ڭࢣ͋ΓֶशͰྑ͍ग़ྗʹͳΔΑ͏ʹֶश fθ ̂ y x y L(y, ̂
y)
ݱ࣮ɿਪ݁ՌͱߦಈҰக͠ͳ͍ ਓ͕ؒؒʹೖΔͷͰ ʹͳΔ͜ͱ͕͋Δ ҙࢥܾఆͷঢ়گʹΑͬͯػցͱਓؒͷҙࢥܾఆ͕Ұக͠ͳ͍ ̂ y ≠ a fθ
̂ y x a ≠ ̂ y
ཧɿਓؒͷҙࢥܾఆΛ࠷దԽ ਓؒͷߦಈΛؚΊͯ࠷దԽ͢Δ͜ͱ͕ཧ ͕ͨͩͷग़ྗͰਓؒʹͱͬͯཧղ͍͠ ̂ y y fθ ̂ y
x a = h(x, ̂ y) L(y, a)
ՄࢹԽ ఏҊख๏ɿਓؒͰཧղͰ͖Δํ๏Ͱࢧԉ͍ͨ͠ ਓ͕͍ؒΔͨΊɼޯΛͰ͖ͳ͍ y දݱֶश x ϕ a =
h(z, ̂ y) L(y, a) z
ਓؒͷཧϞσϧΛઃఆͯ͠ɼޯΛՄೳʹʂ y x ϕ a = h(z, x) L(y,
a) h z
දݱΛͬͨదͳՄࢹԽ͍͠ දݱ ͔Βਓ͕ؒཧղͰ͖ΔΑ͏ʹ͢ΔͨΊʹɼ ՄࢹԽͷૢ࡞͕ඞཁ • άϥϑɼը૾ɼϋΠϥΠτͱ͔ʜ ҙࢥܾఆʹରͯ͠ɼྑ͍հೖ͕ߦ͑ΔΑ͏ͳՄࢹԽͦΕ͚ͩͰݚڀʹ ͳΔ͘Β͍͍͠
ຊݚڀͰɼྑͦ͞͏ͳՄࢹԽΛબΜͰར༻͢Δ z
࣮ݧɿͭͷλεΫͰ༗ޮੑΛࣔ͢ λεΫɿߴ࣍ݩσʔλΛ࣍ݩʹѹॖͨ͠ͱ͖ʹ ༗༻ͳදݱΛ֫ಘͰ͖Δ͔ʁ λεΫɿ࣮ࡍͷλεΫͰ ɹɹɹɹ֫ಘͨ͠දݱʹΑΔࢧԉ༗ޮ͔ʁ λεΫɿػց͕Γಘͳ͍Ճใ
ɹɹɹɹදݱͱͯ֫͠ಘͰ͖Δ͔ʁ
λεΫɿྑ͍දݱΛ֫ಘͰ͖Δ͔ʁ ࣍ݩѹॖΛͯ͠σʔλͷՄࢹԽ͕ՄೳʹͳΔ • طଘͷ࣍ݩѹॖ౷ܭతͳ࠷దԽ͔͠ߟ͍͑ͯͳ͍ ߴ࣍ݩͳσʔλΛਓతʹ࡞ΓɼྨʹऔΓΉ • ަࣹӨͨ࣌͠ʹɼz9zͱz0zͷܗʹฒͿΑ͏ʹ࡞
λεΫɿදݱϞσϧͱཧϞσϧ දݱϞσϧ • Yͷઢܕࣸ૾ߦྻ ཧϞσϧ • ҰͰYͷΈࠐΈωοτϫʔΫ • ਓؒͷࢹ֮Λ͓͓·͔ʹ࠶ݱ͢Δ
λεΫɿ݁Ռ "DDVSBDZˠ ͷ࣮ݧࢀՃऀ͕ਫ਼Λୡ
λεΫɿϦΞϧͳσʔλͰࢧԉͰ͖Δ͔ ϩʔϯ৹ࠪΛࡐʹͨ͠λεΫ • ࡁͨ͠ɼ ೲɼ ঝೝɼ ڋ൱ • ଛࣦؔɿ
.5VSLͰࢀՃऀΛूΊܭճΛूΊͨ ඪɿදݱʹΑΔΞυόΠεͰ ҙࢥܾఆͷࢧԉ͕Մೳ͔Ͳ͏͔ y = 1 y = 0 a = 1 a = 0 l(y, a) = 1y≠a
λεΫɿإදʹΑͬͯදݱΛՄࢹԽ 'BDJBMBWBUBSΛͬͯɼإදͰՄࢹԽΛߦ͏ • $IFSOP ff GBDFTإύʔπʹͦΕͧΕ͕ରԠͯ͠มԽ
λεΫɿදݱϞσϧͱཧϞσϧ දݱϞσϧ • શ݁߹ͷϢχοτΛ ཧϞσϧ • શ݁߹ͷϢχοτΛ
λεΫɿతͳΞυόΠεͱಉ /PBEWJDFΑΓ্ ༧ଌΞυόΠεͱಉ
λεΫɿਓ͔ؒ͠Γಘͳ͍ใ֫ಘͰ͖Δ͔ ਓ͔ؒ͠Γಘͳ͍ใʢࣝɼৗࣝͱ͔ʣΛදݱͱͯ֫͠ಘ Ͱ͖Δ͔ΛΈ͍ͨ ҩྍஅͷλεΫΛઃܭ • Ճใ Λઃఆ͢Δˠਓ͔ؒ͠ݟΕͳ͍ • ͜ͷՃใग़ྗʹӨڹΛٴ΅͢ઃఆ
σʔληοτࣗମਓతʹੜ s
λεΫɿදݱϞσϧͱཧϞσϧ දݱϞσϧ • ॏΈͱಛྔͷઢܗ ཧϞσϧ • ॏΈͱಛྔͷઢܗ Ճใͷઢܗ
λεΫɿ • ७ਮʹ܇࿅Λߦ͏߹ .P. • දݱҰॹʹ܇࿅͢Δ .P.Ҏ֎ͰɼՃใʹ Αͬͯաֶश͕ى͖͍͢
h(.BDIJOF)
·ͱΊͱײ ·ͱΊ ਓ͔ؒΒਓؒͷͨΊʹҙࢥܾఆΛࢧԉ͢Δ ϑϨʔϜϫʔΫΛఏҊ ਓؒͷ࠷ऴܾఆΛࢧԉͰ͖ΔΑ͏ʹɼදݱΛֶश͠ՄࢹԽ