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
吹っ飛んだ布団, その裏側と行方
Search
yuki.s
January 23, 2019
Technology
0
550
吹っ飛んだ布団, その裏側と行方
ダジャレ案件における、オフトゥンフライングシステム開発の経緯について、Shareka開発担当者がお話します。
yuki.s
January 23, 2019
Tweet
Share
Other Decks in Technology
See All in Technology
本が全く読めなかった過去の自分へ
genshun9
0
720
強化されたAmazon Location Serviceによる新機能と開発者体験
dayjournal
3
260
解析の定理証明実践@Lean 4
dec9ue
1
200
Connect 100+を支える技術
kanyamaguc
0
160
KubeCon + CloudNativeCon Japan 2025 Recap by CA
ponkio_o
PRO
0
250
Tech-Verse 2025 Global CTO Session
lycorptech_jp
PRO
0
1.2k
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
110
MUITにおける開発プロセスモダナイズの取り組みと開発生産性可視化の取り組みについて / Modernize the Development Process and Visualize Development Productivity at MUIT
muit
0
770
2025-06-26_Lightning_Talk_for_Lightning_Talks
_hashimo2
2
120
mrubyと micro-ROSが繋ぐロボットの世界
kishima
2
380
GeminiとNotebookLMによる金融実務の業務革新
abenben
0
250
Yamla: Rustでつくるリアルタイム性を追求した機械学習基盤 / Yamla: A Rust-Based Machine Learning Platform Pursuing Real-Time Capabilities
lycorptech_jp
PRO
4
180
Featured
See All Featured
A Modern Web Designer's Workflow
chriscoyier
694
190k
Java REST API Framework Comparison - PWX 2021
mraible
31
8.7k
BBQ
matthewcrist
89
9.7k
What’s in a name? Adding method to the madness
productmarketing
PRO
23
3.5k
How GitHub (no longer) Works
holman
314
140k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
29
9.5k
We Have a Design System, Now What?
morganepeng
53
7.7k
Six Lessons from altMBA
skipperchong
28
3.9k
The Cost Of JavaScript in 2023
addyosmani
51
8.5k
Building Applications with DynamoDB
mza
95
6.5k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
20
1.3k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
46
9.6k
Transcript
5 ,. 1
2 • • •
• • ()
3 Qiita https://qiita.com/fujit33/items/dbfbd7a2aa3858067b6c • Qiita •
4 • $ • • $
• !# " !#
5
• •
6 " $% ()&+ () * -, Raspberry Pi ' #!#
Shareka Ukeruka Kurohige “AI”rWeave CsG-*78VcAI DeepLearning-*78m]AI ^QJjv\~o(:*: $
#S 4dg |Y}Z t FWIKn6352w<0,)'(:/&+1 _-*78#;` kA KBDJPMq#N 95:.+1() e [Lr#R a@i y2, ?" y0,)'(:/&+1 =Obx zlU Ef#Tp ! >X#uh H{!4'*%:
8 https://dajare.jp/ 45,000
9 7;! /7;! 9 /7;! ="7;! '0.1+ !2
&) /- 2* 3 ?> +0% math AI' ,3( "#*$15 .%8#(<! ,$- 4&) :6 update
B C 10 L LG • - - • M
N • • • • •
11
( ) 12
13 c 5 75 24 620
1 9 a 999 / 4 1 34252583 cS
14 4 4 3 0 5
• 30,000 • Ukeruka model prototype • character-level CNN 1 6 A27 8 9I
15 4 4 3 0 5
• 30,000 • Ukeruka model prototype • character-level CNN 1 6 A27 8 9I
16 ! 8 Q 4 !
! !! ! ! ! ! ! ! ! ! ! ! ! 1 3 0 • # 30,0004 • Ukeruka model prototype • character-level CNN i 6 I 7 1 3 e A 7B:.LightGBM1@ Character-level CNN1@ i i 6; 2- /= 5<, C9 W 65 5 ?8 • (*A3 • &!$% • D>larity • XGBuuton FuttoButon • &$+&)+ "' 002 9
17 • G5$#!&"01 • 3:4)->;-+* • 2? ,<
update • 8@ D7 • 9I>;HA • /C6B/C9.-F=H A • G5 JE'(%K6