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
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Yuichiro Someya
November 06, 2018
Programming
2.1k
3
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
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
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
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
460
How we use GPUs in Cookpad
ayemos
0
200
Other Decks in Programming
See All in Programming
Semantic Version 単位で戦略を柔軟に変えて、パッケージアップデートを自動化する
daitasu
1
300
なぜ型を書くのか? TSKaigi2026で改めて考える #tskaigi_smarthr
kajitack
0
150
AI時代のUIはどこへ行く?その2!
yusukebe
22
7.5k
Datadog LLM Observabilityで実現する 安全なLLM Usage 管理
3150
0
110
過去最大のMCPアップデート! 2026-07-28 RC版の謎に迫る
licux
6
390
ローカルLLMでどこまでコードが書けるか -拡張版 / How much code can be written on a local LLM Extended
kishida
12
4.4k
鹿野さんに聞く!『TypeScriptコードレシピ集』で磨く実践力
tonkotsuboy_com
3
780
フロントエンドとバックエンドで「1文字」を揃えよう
youkidearitai
PRO
0
740
Mujeres en SEO Summit 2026 - Greatest Disaster Hits en Web Performance
guaca
0
200
さぁV100、メモリをお食べ・・・
nilpe
0
150
Inside Stream API
skrb
1
770
Strategic Design in the Frontend: Moduliths & Micro Frontends @DDDEurope
manfredsteyer
PRO
0
130
Featured
See All Featured
How to optimise 3,500 product descriptions for ecommerce in one day using ChatGPT
katarinadahlin
PRO
1
3.6k
AI Search: Where Are We & What Can We Do About It?
aleyda
0
7.6k
Into the Great Unknown - MozCon
thekraken
41
2.6k
A designer walks into a library…
pauljervisheath
211
24k
Ecommerce SEO: The Keys for Success Now & Beyond - #SERPConf2024
aleyda
1
2k
Leveraging LLMs for student feedback in introductory data science courses - posit::conf(2025)
minecr
1
300
Imperfection Machines: The Place of Print at Facebook
scottboms
270
14k
The agentic SEO stack - context over prompts
schlessera
0
820
<Decoding/> the Language of Devs - We Love SEO 2024
nikkihalliwell
1
260
Designing for Performance
lara
611
70k
It's Worth the Effort
3n
188
29k
Navigating Weather and Climate Data
rabernat
0
240
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