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
Real World Machine Learning
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Yuichiro Someya
January 21, 2017
Programming
0
7k
Real World Machine Learning
Cookpad TechConf 2017 01/21
https://techconf.cookpad.com/2017/
Yuichiro Someya
January 21, 2017
Tweet
Share
More Decks by Yuichiro Someya
See All by Yuichiro Someya
にんげんがさき 基盤はあと / Developers over ML platform
ayemos
0
15k
機械学習をスモールスタートさせる方法 / small machine learning
ayemos
3
2.1k
アットホームな分析基盤の作り方 / Homemade Machine Learning Toolkits
ayemos
1
1k
サービス開発、機械学習、クラウド / the trinity of machine learning
ayemos
0
3.6k
成長を止めない機械学習のやり方 / Don't stop 'til you get enough (data).
ayemos
15
5.3k
AWS で加速する機械学習 / Accelerate Machine Learning with AWS
ayemos
1
360
クックパッドの機械学習基盤 2018 / Machine Learning Platform at Cookpad ~ 2018 ~
ayemos
15
21k
PyTorchとCaffe2とONNXと深層学習モデルのデプロイについて
ayemos
1
3.1k
クックパッドにおけるAWS GPUインスタンスの利用事例 / Powering by AWS GPU Instances in Cookpad Inc
ayemos
0
450
Other Decks in Programming
See All in Programming
AIと共にエンジニアとPMの “二刀流”を実現する
naruogram
0
100
Codex CLIのSubagentsによる並列API実装 / Parallel API Implementation with Codex CLI Subagents
takatty
2
690
20260320登壇資料
pharct
0
130
存在論的プログラミング: 時間と存在を記述する
koriym
5
570
AI 開発合宿を通して得た学び
niftycorp
PRO
0
180
おれのAgentic Coding 2026/03
tsukasagr
1
120
車輪の再発明をしよう!PHP で実装して学ぶ、Web サーバーの仕組みと HTTP の正体
h1r0
2
440
今こそ押さえておきたい アマゾンウェブサービス(AWS)の データベースの基礎 おもクラ #6版
satoshi256kbyte
1
210
Nostalgia Meets Technology: Super Mario with TypeScript
manfredsteyer
PRO
0
110
飯MCP
yusukebe
0
400
今からFlash開発できるわけないじゃん、ムリムリ! (※ムリじゃなかった!?)
arkw
0
160
Mastering Event Sourcing: Your Parents Holidayed in Yugoslavia
super_marek
0
130
Featured
See All Featured
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.7k
The Organizational Zoo: Understanding Human Behavior Agility Through Metaphoric Constructive Conversations (based on the works of Arthur Shelley, Ph.D)
kimpetersen
PRO
0
280
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
34
2.7k
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
430
The #1 spot is gone: here's how to win anyway
tamaranovitovic
2
1k
Groundhog Day: Seeking Process in Gaming for Health
codingconduct
0
130
B2B Lead Gen: Tactics, Traps & Triumph
marketingsoph
0
86
Scaling GitHub
holman
464
140k
Test your architecture with Archunit
thirion
1
2.2k
RailsConf 2023
tenderlove
30
1.4k
Marketing to machines
jonoalderson
1
5.1k
The untapped power of vector embeddings
frankvandijk
2
1.6k
Transcript
Real World Machine Learning Cookpad TechConf 2017
BZFNPTNF છ୩༔Ұ<:VJDIJSP4PNFZB> ౦େେֶӃܭࢉֶઐ߈म࢜ ΫοΫύου৽ଔ ݚڀ։ൃ෦ UXJUUFS!BZFNPT@Z HJUIVCBZFNPT XFCBZFNPTNF
છ୩༔Ұ<:VJDIJSP4PNFZB>
BZFNPTNF BZFNPTNF
$PPLQBE5FDI$POG BZFNPTNF ΫοΫύο υ ʹ ͓ ͚ Δ σΟ
ʔ ϓ ϥ ʔ χ ϯάͷ Φ Ϟ ς ϥ $PPLQBE5FDI$POG BZFNPTNF
$PPLQBE5FDI$POG BZFNPTNF ΦϞς ද
$PPLQBE5FDI$POG BZFNPTNF
$PPLQBE5FDI$POG BZFNPTNF
$PPLQBE5FDI$POG BZFNPTNF ΈࠐΈχϡʔϥϧωοτϫʔΫΛར༻ͨ͠νʔϜ͕ѹউ *NBHF/FU-BSHF4DBMF 7JTVBM3FDPHOJUJPO $IBMMFOHF ݸͷΧςΰϦʹ͚ΒΕͨը૾ͷೝࣝਫ਼Λڝ͏ࠃࡍతίϯςετ $PPLQBE5FDI$POG BZFNPTNF
$PPLQBE5FDI$POG BZFNPTNF
$PPLQBE5FDI$POG BZFNPTNF ΫοΫύουݚڀ։ൃ෦ൃ
$PPLQBE5FDI$POG BZFNPTNF
$PPLQBE5FDI$POG BZFNPTNF ྉཧ͖Ζ͘ ެ։
$PPLQBE5FDI$POG BZFNPTNF εϚʔτϑΥϯͷࣸਅͷɺྉཧΛࣗಈతʹऩूʗه $BGGF/FUͷ'JOFUVOJOHʹΑΔྉཧը૾ೝࣝ ݄ݱࡏ ਓҎ্ͷϢʔβʔ͕ར༻
ຕҎ্ͷࣸਅΛఆ ྉཧ͖Ζ͘
$PPLQBE5FDI$POG BZFNPTNF σΟʔϓϥʔχϯάಋೖاۀ
$PPLQBE5FDI$POG BZFNPTNF ݚڀ։ൃ෦ͷൃ໊ͷ৫ σΟʔϓϥʔχϯάΛར༻ͨ͠ॳͷϓϩμΫτΛެ։ ΫοΫύουʷσΟʔϓϥʔχϯά ΦϞς
$PPLQBE5FDI$POG BZFNPTNF 63" ϥ
$PPLQBE5FDI$POG BZFNPTNF ڥͮ͘Γ
$PPLQBE5FDI$POG BZFNPTNF ܭࢉػڥͷվળ
$PPLQBE5FDI$POG BZFNPTNF ܭࢉػڥߏஙͷޮԽ
$PPLQBE5FDI$POG BZFNPTNF "NB[PO&$ͷ(16Πϯελϯε HQ Λը૾ೝࣝʹར༻ 6CVOUVUSVTUZ͔ΒखಈͰηοτΞοϓ ڥͷߏஙʗཧ͕େม
࣌ͷঢ়گ ܭࢉػڥߏஙͷޮԽ OPVWFBVͷແޮԽ OWJEJBESJWFSͷΠϯετʔϧ $6%"$6%//ͷΠϯετʔϧ $IBJOFS5FOTPSqPX$B⒎FͷΠϯετʔϧ ڥมͷઃఆ
$PPLQBE5FDI$POG BZFNPTNF ը૾ೝࣝλεΫʹඞཁͳڥΛશ෦ͤͨ͠".*Λ1BDLFSʹΑΓ࡞ खॱͷίʔυԽ ࣮ߦͷࣗಈԽ dఔͰ࡞ۀ։࢝ՄೳͳΦϯσϚϯυ(16ڥΛܧଓతʹ࣮ݱ
৽ͨͳϦαʔνϟʔʗσϕϩούʔΛεϜʔζʹड͚ೖΕՄೳ ܭࢉػڥߏஙͷޮԽ
$PPLQBE5FDI$POG BZFNPTNF .--VODI.-$MBTT
$PPLQBE5FDI$POG BZFNPTNF .--VODI෦һʹΑΔ࣋ͪճΓͰͷߨ ٛΛ िҰճ ࣮ࢪ ڧԽֶश $IBJOFS
"84 %BSL/FU "NB[PO-FY"MFYB .-$MBTT݄ҰճΛ҆ʹɺ֎෦͔Β ߨࢣΛট͍ͯߨٛΛ࣮ࢪ .--VODI.-$MBTT
$PPLQBE5FDI$POG BZFNPTNF ·ͱΊ
$PPLQBE5FDI$POG BZFNPTNF σΟʔϓϥʔχϯάΛར༻ͨ͠ϓϩμΫτΛެ։ ৫ͱͯ͠ܧଓతʹ͢Δҝͷڥͮ͘ΓʹऔΓΜͰ͍Δ ݚڀ։ൃڥͷΤϯδχΞϦϯάʹΑΔվળ ෦ͷࣝڞ༗ͳͲ࣌ؒΛͬͯ
ΫοΫύουʷσΟʔϓϥʔχϯά