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
33
[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
29
[読み会] “Are You Really Sure?” Understanding the Effects of Human Self-Confidence Calibration in AI-Assisted Decision Making
mei28
0
120
[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
680
[CHI'24] Fair Machine Guidance to Enhance Fair Decision Making in Biased People
mei28
0
85
[DEIM2024] 卓球の得点予測における重要要素の分析
mei28
0
52
[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
230
[読み会] Words are All You Need? Language as an Approximation for Human Similality Judgements
mei28
0
52
[参加報告] AAAI'23
mei28
0
110
[計算機構論] Learning Models of Individual Behavior in Chess
mei28
0
87
Featured
See All Featured
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
Statistics for Hackers
jakevdp
799
220k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
10
1k
Six Lessons from altMBA
skipperchong
28
4k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
18
1.1k
Designing for Performance
lara
610
69k
Why Our Code Smells
bkeepers
PRO
338
57k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
33
2.4k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
34
3.1k
The Art of Programming - Codeland 2020
erikaheidi
55
13k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
9
780
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