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
DeepLearningBook 9.3-9.4
Search
mtjuney
January 16, 2018
Technology
0
47
DeepLearningBook 9.3-9.4
9.3 Pooling
9.4 Convolution and Pooling as an Infinitely Strong Prior
mtjuney
January 16, 2018
Tweet
Share
More Decks by mtjuney
See All by mtjuney
DeepLearningBook 9.5-9.7
mtjuney
0
44
Other Decks in Technology
See All in Technology
データの整合性を保ちたいだけなんだ
shoheimitani
8
3.1k
AzureでのIaC - Bicep? Terraform? それ早く言ってよ会議
torumakabe
1
550
FinTech SREのAWSサービス活用/Leveraging AWS Services in FinTech SRE
maaaato
0
130
こんなところでも(地味に)活躍するImage Modeさんを知ってるかい?- Image Mode for OpenShift -
tsukaman
0
140
Data Hubグループ 紹介資料
sansan33
PRO
0
2.7k
セキュリティについて学ぶ会 / 2026 01 25 Takamatsu WordPress Meetup
rocketmartue
1
300
AI駆動PjMの理想像 と現在地 -実践例を添えて-
masahiro_okamura
1
110
We Built for Predictability; The Workloads Didn’t Care
stahnma
0
140
マーケットプレイス版Oracle WebCenter Content For OCI
oracle4engineer
PRO
5
1.6k
Sansan Engineering Unit 紹介資料
sansan33
PRO
1
3.8k
AIと新時代を切り拓く。これからのSREとメルカリIBISの挑戦
0gm
0
920
Bill One 開発エンジニア 紹介資料
sansan33
PRO
4
17k
Featured
See All Featured
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
450
Faster Mobile Websites
deanohume
310
31k
End of SEO as We Know It (SMX Advanced Version)
ipullrank
3
3.9k
Designing for humans not robots
tammielis
254
26k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
141
34k
Navigating Algorithm Shifts & AI Overviews - #SMXNext
aleyda
0
1.1k
Between Models and Reality
mayunak
1
190
Code Review Best Practice
trishagee
74
20k
Making the Leap to Tech Lead
cromwellryan
135
9.7k
SERP Conf. Vienna - Web Accessibility: Optimizing for Inclusivity and SEO
sarafernandez
1
1.3k
Tell your own story through comics
letsgokoyo
1
810
Darren the Foodie - Storyboard
khoart
PRO
2
2.4k
Transcript
Deep Learning Book 9.3-9.4 mtjuney
• ը૾ೝࣝʹ͓͍ͯ ը૾ͷେ͖͖͕͞มΘͬͨͱ͖Ͱಉ͡ग़ྗ͕ग़ͯཉ͍͠ • ࣮ࡍมΘͬͯ͠·͏ • ͦ͜ͰPooling 9.3 Pooling Apple
• Pooling • ग़ྗΛԿΒ͔ͷ౷ܭྔͰஔ͖͑Δ • ౷ܭྔ: ࠷େɺฏۉɺL2ϊϧϜ etc 9.3 Pooling
{ { { ࠷େ ࠷େ ࠷େ ྫ: ࠷େPooling
9.3 Pooling • ೖྗͷখ͞ͳҠಈʹରͯ͠ෆมʹͳΔ • খ͞ͳεέʔϦϯάɺճసɺҠಈʹରͯ͠ؤ݈ • ग़ྗͷϢχοτ͕ݮ͞ΕΔ • ܭࢉྔݮ
{ { { • ՄมͷೖྗʹରԠͰ͖Δ • ՄมΛݻఆʹམͱ͠ࠐΉ 9.3 Pooling ࠷େ
࠷େ ࠷େ
9.3 Pooling • ՄมͷೖྗʹରԠͰ͖Δ • Global Average Pooling[Lin 2013] •
νϟωϧຖʹฏۉΛग़͢ • શ݁߹ͷΘΓʹΘΕͨΓ͢Δ
• Maxout Network [Goodfellow 2013] • νϟωϧ୯ҐͰͷPooling • ҟͳΔಛʹԠ͢ΔϑΟϧλͷ͏ͪɺ ͲΕ͔ҰͭͰԠ͢Εग़ྗԠ͢Δ
9.3 Pooling
• Infinitely Strong Priorʢແݶʹڧ͍ࣄલʣ • ύϥϝʔλ͕͍͔ͭ͘ͷʹͳΔ֬Λ0ʹͯ͠ શʹ༻ېࢭͱ͢Δ • ΈࠐΈωοτϫʔΫશ݁߹ωοτϫʔΫʹ ແݶʹڧ͍ࣄલΛ༩͑ͨͷͱྨࣅ
• ۙҎ֎ͷॏΈ͕0 • ॏΈΛڞ༗ • Poolingಉ༷ • ೖྗ͕খ͞ͳҠಈʹରͯ͠ෆม 9.4 Convolution and Pooling as an Infinitely Strong Prior
• ͜ΕΒͷࣄલԾఆ͕ଥͰ͋Ε༗ޮ • ଥͰͳ͍߹ɺUnderfittingͷݪҼͱͳΔ • Pooling • ͋Δಛ͕ग़Δݫີͳॴ͕Γ͍ͨ߹ٯޮՌ • GANͷֶशͳͲͷಛఆͷλεΫʹٯޮՌ
• ΈࠐΈ • ΕͨॴͷใΛ͍͍ͨ߹ɺٯޮՌ 9.4 Convolution and Pooling as an Infinitely Strong Prior
• ΈࠐΈϞσϧΈࠐΈϞσϧͷΈͱൺֱ͞ΕΔ͖ • ΈࠐΈϞσϧ • ઃܭऀ͕ۭؒతࣝΛΈࠐΜͰ͍Δ • ΈࠐΈͰͳ͍Ϟσϧ • ۭؒతࣝΛֶशͰ֫ಘ͢Δඞཁ͕͋Δ
• ͜ΕΒΛಉ͡ϕϯνϚʔΫͰൺֱ͢Δ͖Ͱͳ͍ 9.4 Convolution and Pooling as an Infinitely Strong Prior