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
920
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
3.9k
Other Decks in Education
See All in Education
学習指導要領から職場の学びを考えてみる / Thinking about workplace learning from learning guidelines
aki_moon
1
610
Master of Applied Science & Engineering: Computer Science & Master of Science in Applied Informatics
signer
PRO
0
400
コンセプトシェアハウス講演資料
uchinomasahiro
0
360
本の虫になろう
kenjiro56
0
120
CompTIA Security+ SY0-601 Resumo
mariliarochas
2
2.5k
240305_風水輪流轉
learnenergy2
0
130
20240810_ワンオペ社内勉強会のノウハウ
ponponmikankan
2
820
3Dプリンターの使い方(Sovol 06 Plus)
404background
0
270
アニメに学ぶチームの多様性とコンピテンシー
terahide
0
110
HCL Domino 14.0 AutoUpdate を試してみた
harunakano
0
940
謙虚なアジャイルコーチ__アダプティブ_ムーブ_による伴走支援.pdf
antmiyabin
0
220
Droid Knights 2024 Accessibility in Android
nanamare
0
320
Featured
See All Featured
Being A Developer After 40
akosma
84
590k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
7
570
Building Your Own Lightsaber
phodgson
102
6k
A Modern Web Designer's Workflow
chriscoyier
692
190k
Done Done
chrislema
181
16k
Web development in the modern age
philhawksworth
205
10k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
105
48k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
41
9.2k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
92
16k
Build your cross-platform service in a week with App Engine
jlugia
229
18k
Automating Front-end Workflow
addyosmani
1365
200k
A designer walks into a library…
pauljervisheath
202
24k
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