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
機械学習をスモールスタートさせる方法 / small machine learning
Search
Yuichiro Someya
November 06, 2018
Programming
3
1.9k
機械学習をスモールスタートさせる方法 / small machine learning
https://d3m.connpass.com/event/104858/
Yuichiro Someya
November 06, 2018
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
12k
アットホームな分析基盤の作り方 / Homemade Machine Learning Toolkits
ayemos
1
870
サービス開発、機械学習、クラウド / the trinity of machine learning
ayemos
0
3.1k
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
5k
AWS で加速する機械学習 / Accelerate Machine Learning with AWS
ayemos
1
300
クックパッドの機械学習基盤 2018 / Machine Learning Platform at Cookpad ~ 2018 ~
ayemos
15
18k
PyTorchとCaffe2とONNXと深層学習モデルのデプロイについて
ayemos
1
2.8k
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
370
How we use GPUs in Cookpad
ayemos
0
110
Other Decks in Programming
See All in Programming
Micro Frontends for Java Microservices - Devnexus 2024
mraible
PRO
0
470
MicrosoftのPlatform Engineeringガイドを読んで実際になにかやってみた
ymd65536
1
250
Netty Chicago Java User Group 2024-04-17
sullis
0
170
使ってみよう Azure AI Document Intelligence
kosmosebi
2
270
educure_カリキュラム生操作マニュアル.pdf
linew_official
0
640
Front-end application development, Symfony-style(s)
dunglas
2
2k
Prepare for Jakarta EE 11 - Performance and Developer Productivity
ivargrimstad
0
670
#phpcon_odawara オープン・クローズドなテストフィクスチャを求めて / open closed test fixtures
77web
3
220
チーム力を高めるスクラム実践法:カンバン公開と課題攻略について - ニフティのスクラムトーク Vol. 2 - NIFTY Tech Talk #18
niftycorp
PRO
1
110
Changed Rules: Architectures with Lightweight Stores
manfredsteyer
PRO
0
240
単体テストを書かない技術 #phpcon_odawara
o0h
PRO
26
8.1k
新宿ダンジョンを可視化してみた
satoshi7190
2
210
Featured
See All Featured
Designing for humans not robots
tammielis
248
25k
GraphQLとの向き合い方2022年版
quramy
31
12k
How GitHub (no longer) Works
holman
304
140k
The Pragmatic Product Professional
lauravandoore
24
5.8k
How To Stay Up To Date on Web Technology
chriscoyier
782
250k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
124
32k
KATA
mclloyd
14
12k
Code Reviewing Like a Champion
maltzj
513
39k
Into the Great Unknown - MozCon
thekraken
10
990
Automating Front-end Workflow
addyosmani
1355
200k
Become a Pro
speakerdeck
PRO
10
4.5k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
240
1.2M
Transcript
ػցֶशΛεϞʔϧελʔτ ͤ͞Δํ๏ ΫοΫύουגࣜձࣾછ୩༔Ұ %BUB%SJWFO%FWFMPQFS.FFUVQ
ࣗݾհ છ୩༔Ұ<BZFNPT> ΫοΫύουגࣜձࣾ৽ଔೖࣾ ݚڀ։ൃ෦ΤϯδχΞ ػցֶशج൫ɺը૾ೝࣝܥͷݚڀ։ൃ
ΫοΫύουͱػցֶश ΫοΫύουݚڀ։ൃ෦ ݄ʹൃ ࢲ͕ଐ͞Εͨͷಉ࣌ظ ໊࣌ͷϝϯόʔ
݄ݱࡏࠃʹ໊ ւ֎ʹ໊ ʰສͷϨγϐσʔλΛ׆༻͠ɺϢʔβʔʹՁΛಧ͚Δʱ
ࠓͷτϐοΫ ػցֶश ओʹਂֶश Λ εϞʔϧελʔτͤ͞Δํ๏ ͳͥεϞʔϧελʔτ͕ඞཁ͔ Ͳ͏Δͷ͔
ࠓͷτϐοΫ ٕज़ʗέʔεελσΟগͳΊɺ ίϯηϓτଟΊͷʹͳΓ·͢ աڈʹٕͨ͠ज़తͳͪ͜Β IUUQTTQFBLFSEFDLDPNBZFNPT
ਂֶशͱεϞʔϧελʔτ
ਂֶशͱεϞʔϧελʔτ 4NBMMTUBSU εϞʔϧελʔτ 4UBSUTNBMM
lUIJOLJOHCJH TUBSUJOHTNBMM BOETDBMJOHGBTUz IUUQTKJNDBSSPMMDPNJOOPWBUJPOUIJOLCJHTUBSUTNBMMTDBMFGBTU
5IJOLCJHJEFOUJGZUIFMPOHUFSNUSBOTGPSNBUJWFUSFOET JODMVEJOHTJHOJpDBOUJOEVTUSZDIBOHF CVTJOFTTNPEFM EJTSVQUJPO ྫ͑ɺʮσΟʔϓϥʔχϯάΛ͍ͬͯ͘ʯͱܾΊΔ
4UBSUTNBMM1JDLBOVNCFSPGTNBMM FYQFSJFOUJBM PSJFOUBUFEQSPKFDUTUPCFHJO5IJTXJMMHJWFZPVCFUUFS EFQUIPGJOTJHIU ͍ͬͯͨ͘Ίʹখ͍͞ϓϩδΣΫτΛ͜ͳ͠ɺֶͿ
4DBMFGBTU%FUFSNJOFXIJDIBSFBTOFFEUPCFUBDLMFE pSTUJOUFSNTPGNPWJOHGPSXBSE%FWFMPQUIFBCJMJUZUP UBLFZPVSbQSPUPUZQJOH`PGTLJMMTFOIBODFNFOUGSPNUIF TNBMMTDBMFQSPKFDUTJOUPGVMMqFEHFEPQFSBUJPOT ༗ͳϓϩδΣΫτΛબͼɺຊ֨తʹՔಇͤ͞Δ
5IJOLCJH ྫ͑ ʮਂֶशΛ͍ͬͯ͘ʯͱܾΊΔ 4UBSUTNBMMখ͍͞ϓϩδΣΫτ ࣮ݧ Λ͜ͳ͠ɺֶͿ 4DBMFGBTU༗ͳϓϩδΣΫτΛຊ֨తʹՔಇͤ͞Δ
ਂֶशͱ4UBSUTNBMM 4UBSUTNBMMখ͍͞ϓϩδΣΫτΛ͜ͳ͠ɺֶͿ ਂֶशͱ4UBSUTNBMMͷ૬ੑ͕͍͍ͱࢥΘͤΔ ৽ٕज़Ͱ͋ΓɺԿ͕ͲΕ͘Β͍Ͱ͖Δͷ͔प͞Ε͍ͯͳ͍ ෦తࢼߦࡨޡ͕ඞཁ
લྫͳ͍ͷͰɺޭ ྫϢʔβʔͷՁʹܨ͕Δ ͢Δͷ͔͔Βͳ͍ ֎෦తʏ ٕज़ελοΫͱͯ͠ݟͯૣख़Ͱ͋Δ ӡ༻ͷٕज़తशख़͕ඞཁ
ਂֶशͱ4UBSUTNBMM ҰํͰɺ4UBSUTNBMM͕Γʹͦ͘͏ͳҰ໘͋Δ େྔͷσʔλͱܭࢉث͕ඞཁ ӡ༻ίετ͕ߴ͍ ࠾༻େมͦ͏
IUUQTBJHPPHMFSFTFBSDIQVCTQVC
ਂֶशͱ4UBSUTNBMM ҰํͰɺ4UBSUTNBMM͕Γʹͦ͘͏ͳҰ໘͋Δ େྔͷσʔλͱܭࢉث͕ඞཁ ӡ༻ίετ͕ߴ͍ ࠾༻େมͦ͏
IUUQTBJHPPHMFSFTFBSDIQVCTQVC .-0QTͰ ͕ ղܾͰ͖ͦ͏ͳ
ͱ͜ΖͰ.-0QTͱ ڪΒ͘%FW0QTಉ༷͕ͩ ·ͩఆٛෆ໌ྎ ֶशΞϧΰϦζϜҎ֎ʁ %FW0QTͷ.-൛ʁ ػցֶश͕ɺιϑτΣΞ։ൃࣄۀʹ͓͍ͯՁΛੜΈग़͢͜ͱͷͰ͖Δ
ٕज़ελοΫͰ͋Γଓ͚ΔͨΊʹඞཁͳٕज़ ʰӡ༻ίετͷݮʱ͚͕ͩతͰͳ͍ ྫਂֶशΛεϞʔϧελʔτͤ͞Δҝͷ.-0QT
͜͜·Ͱ·ͱΊ ਂֶशΛεϞʔϧελʔτ͍ͤͨ͞ ͦͷͨΊʹ.-0QTͷϓϥΫςΟεΛ׆͔ͤͦ͏
εϞʔϧελʔτͷͨΊͷ.-0QT ΫοΫύουͷ߹
ܭࢉثڥ ݄ͷ ݚڀ։ൃ෦һਓ དྷि͔ΒΠϯλʔϯΛਓड͚ೖΕ "84ຊ൪ΞΧϯτʹྑͷ(16Πϯελϯε HYMBSHF ͕
৽ن࡞ͷʹίϛϡχέʔγϣϯ͕ൃੜ ݚڀ։ൃ༻ΞΧϯτΛൃߦ͠ɺӡ༻ͷੵۃతͳԽ
ܭࢉثڥ ݚڀ։ൃ༻ΞΧϯτͷΠϯϑϥΛίʔυཧ ຊ൪ΞΧϯτͷϓϥΫςΟε %FW0QT ʹ฿͏ $IBU#PUΛ௨ͯ͠(16ΠϯελϯεΛ্ཱͪ͛ΔΈΛ࣮
Πϯελϯεͷ࡞ɺٳΠϯελϯεͷࣗಈఀࢭΛඋ ࣮࣭ (16Πϯελϯεݐͯ์Λ࣮ݱ ͍ͭͰ࣮ݧεϞʔϧελʔτ
ܭࢉثڥ ݚڀ։ൃ༻ΞΧϯτͷΠϯϑϥΛίʔυཧ ຊ൪ΞΧϯτͷϓϥΫςΟε %FW0QT ʹ฿͏ $IBU#PUΛ௨ͯ͠(16ΠϯελϯεΛ্ཱͪ͛ΔΈΛ࣮
Πϯελϯεͷ࡞ɺٳΠϯελϯεͷࣗಈఀࢭΛඋ ࣮࣭ (16Πϯελϯεݐͯ์Λ࣮ݱ ͍ͭͰ࣮ݧεϞʔϧελʔτ .-0QT
ػցֶशج൫ͱ4UBSUTNBMM ػցֶशج൫·ͨ৽͍͠ྖҬ4UBSUTNBMM͕ඞཁ ඞཁͳͷج൫ٕज़ͷεϞʔϧͳࢼߦࡨޡ ྫ͑ج൫୲Λ3%ʹஔͯ͠ΈΔ LVCFqPXͳͲͷϓϥοτϑΥʔϜ৫γνϡΤʔγϣϯ ͱͷ૬ੑ͕͋Δ
ՄೳͰ͋Ε ੵۃతʹࢼ͢ɺͬͯΈΔͱΑͦ͞͏
༨ஊʙݕࡧγεςϜʹֶͿʙ ʮσʔλͷྲྀΕ͕͋ΓɺγεςϜ͕σʔλͱڞʹ͢ΔΑ͏ͳγ εςϜʯͱ͍͑ʁ ݕࡧγεςϜͷӡ༻ϓϥΫςΟε͔Β ֶͿ͜ͱଟͦ͏ ΠϯσοΫεͷߏஙɺࣙॻσʔλͷཧ IUUQTXXXBNB[PODPKQ#VJMEJOH*OUFMMJHFOU4ZTUFNT-FBSOJOH&OHJOFFSJOHFCPPLEQ##82)3
·ͱΊ ਂֶशεϞʔϧελʔτ͍ͤͨ͞ ৽͍ٕ͠ज़ͷՄೳੑ ͱ੍ Λ࡞Γͳ͕ΒֶͿ εϞʔϧελʔτ .-0QTͷదͳར༻εϞʔϧελʔτΛॿ͚Δ