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
The fun Deep Learning
Search
Takuya Matsuyama
October 30, 2015
Technology
0
2.8k
The fun Deep Learning
Takuya Matsuyama
October 30, 2015
Tweet
Share
More Decks by Takuya Matsuyama
See All by Takuya Matsuyama
ネイティブモジュールの作り方 @ React Native Meetup #9 in Japan
craftzdog
6
1.3k
How to Create Native Modules @ React Native Japan Meetup #9
craftzdog
1
850
Introducing Inkdrop for Mobile Built with React Native
craftzdog
1
2.2k
Caffeでお手軽本格ディープラーニングiOSアプリ
craftzdog
1
1.6k
Other Decks in Technology
See All in Technology
整頓のジレンマとの戦い〜Tidy First?で振り返る事業とキャリアの歩み〜/Fighting the tidiness dilemma〜Business and Career Milestones Reflected on in Tidy First?〜
bitkey
0
290
React開発にStorybookとCopilotを導入して、爆速でUIを編集・確認する方法
yu_kod
1
100
WordPressから ヘッドレスCMSへ! Storyblokへの移行プロセス
nyata
0
340
無意味な開発生産性の議論から抜け出すための予兆検知とお金とAI
i35_267
0
970
AI導入の理想と現実~コストと浸透〜
oprstchn
0
150
【5分でわかる】セーフィー エンジニア向け会社紹介
safie_recruit
0
26k
生成AI時代 文字コードを学ぶ意義を見出せるか?
hrsued
1
730
より良いプロダクトの開発を目指して - 情報を中心としたプロダクト開発 #phpcon #phpcon2025
bengo4com
1
3.2k
OPENLOGI Company Profile
hr01
0
67k
Snowflake Summit 2025全体振り返り / Snowflake Summit 2025 Overall Review
mtpooh
2
440
生成AI時代の開発組織・技術・プロセス 〜 ログラスの挑戦と考察 〜
itohiro73
1
370
rubygem開発で鍛える設計力
joker1007
2
270
Featured
See All Featured
Why Our Code Smells
bkeepers
PRO
337
57k
Rails Girls Zürich Keynote
gr2m
94
14k
Testing 201, or: Great Expectations
jmmastey
42
7.6k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
VelocityConf: Rendering Performance Case Studies
addyosmani
331
24k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
8
800
Speed Design
sergeychernyshev
32
1k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.3k
How STYLIGHT went responsive
nonsquared
100
5.6k
What’s in a name? Adding method to the madness
productmarketing
PRO
23
3.5k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
48
5.4k
GraphQLとの向き合い方2022年版
quramy
49
14k
Transcript
The fun Deep Learning TAKUYA (@noradaiko) Design Japan
Takuya Matsuyama দࢁ • Twitter: @noradaiko • Freelance since
4 years ago ‣ ex. Yahoo! JAPAN • iOS app, web app developer • Love drawing & playing drums 2
3
walknote music discovery app 4
VTFST 5
Men-kiki ໙ར͖ 6
There are.. a lot of ramen shops in Japan!! 7
Difficult to read & input especially for foreigners 8 Ұའ
ఱԼҰ Ѩར ࢁ಄Ր େউݢ ݹλϯϝϯ ೋ Ұ෩ಊ
can offer ramen shops based on a PHOTO 9
10 +*30TUZMF *OQVU
11 :PLPIBNBGBNJMZTUZMF *OQVU
M e n - k i k i DEMO 12
13 Men-kiki uses Deep Learning technology ʴ ʹ
BCSBODIPGTPDBMMFE"* XIJDIIBT IJHIBDDVSBDZJOJNBHFSFDPHOJUJPO 14 %FFQMFBSOJOHJT
• Inspired by nervous systems of the animal brain •
It can learn features of objects from huge amount of data automatically 15
16 SBNFOJNBHFT -FBSO bXIBUSBNFOJT`
M e n - k i k i ໙ར͖ 17
* English version will be available soon
Deep learning can be also used for.. ART 18
A Neural Algorithm of Artistic Style by Leon A. Gatys,
Alexander S. Ecker, and Matthias Bethge 19 + style
A Neural Algorithm of Artistic Style by Leon A. Gatys,
Alexander S. Ecker, and Matthias Bethge 20 + style
Deep learning can clone the painters’ sense 21
Interesting! 22 + style 1JDBTTP .ZQIPUP 3FTVMU
How about VIDEO? It must be beautiful…
Let’s do it 1. Record videos which will match artistic
style 2. Convert all its frames into artistic style 24
None
None
Wrap up • Deep learning is so fun • Let’s
make great stuff with it!! • Follow me(@noradaiko) on Twitter 27