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
1k
Dockerで機械学習サービスの環境を作ろう!!
ooshita
0
210
事前準備
ooshita
0
190
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
JAWS-UGを通じてアウトプット活動を楽しんでみませんか? #jawsug_tochigi
masakiokuda
0
170
HyRead2425
cbtlibrary
0
120
あきた地域課題解決インターンMarch2025
toyodome
0
290
Ilman kirjautumista toimivia sovelluksia
matleenalaakso
1
20k
Use Cases and Course Review - Lecture 8 - Human-Computer Interaction (1023841ANR)
signer
PRO
0
870
Sanapilvet opetuksessa
matleenalaakso
0
31k
Tips for the Presentation - Lecture 2 - Advanced Topics in Big Data (4023256FNR)
signer
PRO
0
200
MySmartSTEAM2425
cbtlibrary
0
110
Sähköiset kyselyt, kokeet ja arviointi
matleenalaakso
1
18k
1113
cbtlibrary
0
290
Medidas en informática
irocho
0
1.1k
自分にあった読書方法を探索するワークショップ / Reading Catalog Workshop
aki_moon
0
310
Featured
See All Featured
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.4k
The Art of Programming - Codeland 2020
erikaheidi
53
13k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
44
7k
Stop Working from a Prison Cell
hatefulcrawdad
267
20k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
280
13k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Optimising Largest Contentful Paint
csswizardry
34
3.1k
Large-scale JavaScript Application Architecture
addyosmani
510
110k
Building Flexible Design Systems
yeseniaperezcruz
328
38k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
28
9.3k
The Straight Up "How To Draw Better" Workshop
denniskardys
232
140k
Thoughts on Productivity
jonyablonski
69
4.5k
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