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
MolGANの紹介
Search
Oshita Noriaki
June 07, 2019
Education
0
1.1k
MolGANの紹介
Oshita Noriaki
June 07, 2019
Tweet
Share
More Decks by Oshita Noriaki
See All by Oshita Noriaki
第二回 3Dなんでも勉強会
ooshita
1
940
Dockerで機械学習サービスの環境を作ろう!!
ooshita
0
200
事前準備
ooshita
0
180
Edge TPUで 発芽予測をする話
ooshita
0
2.3k
情報幾何の応用と最近の機械学習の動向
ooshita
2
4k
Other Decks in Education
See All in Education
Master of Applied Science & Engineering: Computer Science & Master of Science in Applied Informatics
signer
PRO
0
430
The Blockchain Game
jscottmo
0
3.7k
小・中・高等学校における情報教育の体系的な学習を目指したカリキュラムモデル案/curriculum model
codeforeveryone
2
2.3k
Kindleストアで本を探すことの善悪 #Izumo Developers' Guild 第1回 LT大会
totodo713
0
130
勉強したらどうなるの?
mineo_matsuya
10
6.5k
ACT FAST 20240830
japanstrokeassociation
0
320
Human Perception and Cognition - Lecture 4 - Human-Computer Interaction (1023841ANR)
signer
PRO
0
710
Web Architectures - Lecture 2 - Web Technologies (1019888BNR)
signer
PRO
0
2.7k
Evaluation Methods - Lecture 6 - Human-Computer Interaction (1023841ANR)
signer
PRO
0
700
横浜国立大学大学院 国際社会科学府 経営学専攻博士課程前期(社会人専修コース)_在校生体験談
miki_small_pin
0
700
Flinga
matleenalaakso
2
13k
TP5_-_UV.pdf
bernhardsvt
0
100
Featured
See All Featured
The Invisible Side of Design
smashingmag
298
50k
Measuring & Analyzing Core Web Vitals
bluesmoon
4
130
Making Projects Easy
brettharned
115
5.9k
Building a Modern Day E-commerce SEO Strategy
aleyda
38
6.9k
Adopting Sorbet at Scale
ufuk
73
9.1k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
48k
The Straight Up "How To Draw Better" Workshop
denniskardys
232
140k
Stop Working from a Prison Cell
hatefulcrawdad
267
20k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
47
2.1k
Imperfection Machines: The Place of Print at Facebook
scottboms
265
13k
Agile that works and the tools we love
rasmusluckow
327
21k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
126
18k
Transcript
.PM("/ "OJNQMJDJUHFOFSBUJWFNPEFMGPSTNBMM NPMFDVMBSHSBQIT /JDPMB%F$BP 5IPNBT,JQG ൃදऀɿେԼൣߊ
ຊͷ༰ .PM("/ͱ (SBQI$POWPMVUJPOBM/FUXPSLͱ ("/ͱ .PM("/ͷΞʔΩςΫνϟʔ
ධՁࢦඪ ֶशʹ͓͚Δ
.PM("/ͱ w ͓͓ͬ͟ͺʹ͍͏ͱࢠάϥϑΛੜ͠Α͏ͱ͍͏("/
(SBQI$POWPMVUJPOBM/FUXPSL άϥϑϑʔϦΤม άϥϑԽ
ͳͥ($/Λ͏ͷʁ .4DIMJDIULSVMMFUBM ٙ 3//ϕʔεͷੜϞσϧͷจࣈྻදݱͰ͍͍Μ͡Όͳ͍ͷʁ ͳͥάϥϑʹʁ ͑ 3//ɺ ɾߏจنଇͱදݱͷॱংͷ͍͋·͍͞ͷ྆ํΛֶश͢ΔͨΊʹଟେͳίετΛඅ͢ ɾҰൠతʹʢඇࢠʣάϥϑʹద༻Ͱ͖ͳ͍
("/ min θ max ϕ x∼pdata (x) [logDϕ (x)] +
z∼pz (z) [log(1 − Dϕ (Gθ (z))] ผͰ͖ͳ͍Α͏ʹ͍ͨ͠ ผ͍ͨ͠ (ʹΑͬͯੜͨ͠σʔλ ຊͷσʔλ͔Βֶश
.PM("/ %JTDSJNJOBUPSσʔληοτͱ(FOFSBUPSΛࣝผ͢Δ 3FXBSEOFUXPSL(FOFSBUPSͰੜ͞ΕͨࢠΛධՁ͢Δɽ (FOFSBUPSࢠΛੜ͢Δɽ ɾͦΕͧΕͷ
matrixX = [x1 , …, xN] T ∈ ℝN×T ֤ࢠແάϥϑͰදݱͰ͖Δ
લఏɿ A ∈ ℝN×N×YXIFSFAij ∈ ℝY ྡςϯιϧ ऍߦྻ
3FXBSE/FUXPSL w άϥϑΈࠐΈʹجͮ͘ॱྻෆมหผث͓Αͼใु ωοτϫʔΫʢॴͷԽֶతੑ࣭ʹ͚ͨ3-ϕʔεͷ࠷ దԽͷͨΊʣ w ೖྗάϥϑɼग़ྗεΧϥʔ w %JTDSJNJOBUPSͱಉ͡ωοτϫʔΫΛ༻͢Δɽ
ධՁࢦඪ 4BNBOUBFUBM Uniqueness = ϢχʔΫαϯϓϧ ༗ޮαϯϓϧ Novelty = σʔληοτʹؚ·Εͳ͍༗ޮͳαϯϓϧ ༗ޮͳαϯϓϧ
Validity = 7BMJE શͯͷੜ͞Εͨࢠ
%SVHMJLFOFTTͲͷ͘Β͍Խ߹͕ༀʹͳΔՄೳੑ͕͋Δ͔ 4ZOUIFUJ[BCJMJUZࢠͷ߹ͷ༰қ͞ʢқʣ 4PMVCJMJUZࢠ͕Ͳͷఔਫੑ ਫʹ༹͚͍͔͢ Ͱ͋Δ͔
ࢠؒͷྨࣅͷܭࢉํ๏ʁ "#JDLFSUPOFUBMʹॻ͍͍ͯΔɽ 2&%ͱ͍͏ఆྔతͳਪఆΛߦ͍ͬͯΔɽdͷؒʹΛ࣋ͪɼ ʹ͍ۙ΄Ͳ%SVHMJLFOFTTΛͭɽ QED = exp ( 1 n
n ∑ i=1 ln di) ͜ͷத͕͚ۙΕༀΒ͍͠ͱ͍͑Δ EFTJSBCJMJUZGVODUJPOT B C D E F Gύϥϝʔλ d(x) = a + b [ 1 + exp (− x − c + d 2 e )] 1 − 1 [ 1 + exp (− x − c − d 2 f )] Yࢠهड़ࢠ
݁ 7"&ϕʔεͷੜϞσϧΑΓߴ͍༗ޮੑͱ৽نੑͷ྆ํͰ ࢠάϥϑΛੜ͢Δ͜ͱ͕Ͱ͖Δ ܭࢉ͕࣌ؒҎલͷγʔέϯγϟϧ("/ͱൺֱͯ͠ഒ͍܇࿅࣌ؒ ("/ͱڧԽֶशΛۦ͍ͯ͠ΔͷͰɼϞʔυ่յ͕ى͜Γ͍͢ ͦͷͨΊɼ৽حੑͷ͋Δάϥϑ͕ੜ͞Εʹ͘͘ͳΔ͋ Δɽ