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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Oshita Noriaki
June 07, 2019
Education
0
1.2k
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
1.2k
Dockerで機械学習サービスの環境を作ろう!!
ooshita
0
230
事前準備
ooshita
0
200
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
4.1k
Other Decks in Education
See All in Education
渡辺研Slackの使い方 / Slack Local Rule
kaityo256
PRO
11
11k
CoderDojoへようこそ ニンジャ&保護者向け (CoderDojo Guidance for Ninjas&Parents)
coderdojokodaira
1
100
Pen-based Interaction - Lecture 4 - Next Generation User Interfaces (4018166FNR)
signer
PRO
0
2.1k
The World That Saved Me: A Story of Community and Gratitude
_hashimo2
4
540
Data Presentation - Lecture 5 - Information Visualisation (4019538FNR)
signer
PRO
0
3k
GitHubによるWebアプリケーションのデプロイ / 07-github-deploy
kaityo256
PRO
1
170
栃木県警サイバーセキュリティ研修会2026
nomizone
0
330
Going over the Edge
jonoalderson
0
740
Introduction - Lecture 1 - Information Visualisation (4019538FNR)
signer
PRO
0
5.3k
Leveraging LLMs for student feedback in introductory data science courses (Stats Up AI)
minecr
1
230
環境・社会理工学院(建築学系)大学院説明会 2026|東京科学大学(Science Tokyo)
sciencetokyo
PRO
0
450
心理学を学び活用することで偉大なスクラムマスターを目指す − 大学とコミュニティを組み合わせた学びの循環 / Becoming a great Scrum Master by learning and using psychology
psj59129
1
2k
Featured
See All Featured
How Software Deployment tools have changed in the past 20 years
geshan
0
32k
AI Search: Implications for SEO and How to Move Forward - #ShenzhenSEOConference
aleyda
1
1.1k
Leveraging Curiosity to Care for An Aging Population
cassininazir
1
190
Why Mistakes Are the Best Teachers: Turning Failure into a Pathway for Growth
auna
0
77
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
287
14k
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4k
First, design no harm
axbom
PRO
2
1.1k
We Are The Robots
honzajavorek
0
190
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
254
22k
The Art of Programming - Codeland 2020
erikaheidi
57
14k
Building Flexible Design Systems
yeseniaperezcruz
330
40k
What Being in a Rock Band Can Teach Us About Real World SEO
427marketing
0
190
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