Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
機械学習でサーバの負荷状態を把握したい
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
tsurubee
March 22, 2019
Technology
2.2k
7
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
機械学習でサーバの負荷状態を把握したい
tsurubee
March 22, 2019
More Decks by tsurubee
See All by tsurubee
大規模言語モデルにおけるData-Centric AIと合成データの活用 / Data-Centric AI and Synthetic Data in Large Language Models
tsurubee
1
670
言語モデルによるAI創薬の進展 / Advancements in AI-Driven Drug Discovery Using Language Models
tsurubee
2
670
AIトップカンファレンスからみるData-Centric AIの研究動向 / Research Trends in Data-Centric AI: Insights from Top AI Conferences
tsurubee
3
3.5k
DeepCrysTet: A Deep Learning Approach Using Tetrahedral Mesh for Predicting Properties of Crystalline Materials
tsurubee
0
1.4k
3次元メッシュで表現した結晶構造を用いた材料物性の予測に向けた深層学習モデルの設計 / Design of Deep Learning Model for Predicting Material Properties Using Crystal Structure Represented by Three-Dimensional Mesh
tsurubee
1
2.6k
分散システムの性能異常に対する機械学習の解釈性に基づく原因診断手法 / A Method for Diagnosing the Causes of Performance Issues in Distributed Systems Based on the Interpretability of Machine Learning
tsurubee
0
1.8k
機械学習の解釈性に関する研究動向とシステム運用への応用 / A Survey on Interpretable Machine Learning and Its Application for System Operation
tsurubee
0
400
機械学習モデルの局所的な解釈に着目したシステムにおける異常の原因診断手法の構想
tsurubee
0
8.2k
アニーリングマシンを活用したエッジAIにおける 生成モデルの学習効率化のためのアーキテクチャ
tsurubee
0
1.7k
Other Decks in Technology
See All in Technology
検証フェーズはAIの回答を判断するための学習機会
toru_kubota
2
540
ファミコンでPHPを動かす / PHP on the Famicom side b
tomzoh
0
140
Kiro Crewをはじめよう
kizawa2020
1
110
分析AIエージェントを育てる、動く環境を育てる
codatum
1
480
Essential architectural thinking (revised edition)
ufried
0
110
オンラインゲームのシステム全体像 - コロプラ 2026年度 新卒研修
colopl
0
970
オブザーバビリティを高める AI エージェント体験を考える / Designing AI Agent Experiences That Enhance Observability
aoto
PRO
2
320
ハードウェアコンペでもAI駆動開発が進んでいる話
iotengineer22
1
620
全人類(ほぼ)AWS Organizations の上でAWSを利用している、その世界を知る話
htan
1
130
メルペイ 会計システム概要と歴史
mewuto
0
200
継続的なAIコスト最適化
bgpat
1
260
「Docker Desktop不要の時代」は 来たのか?
ueponx
0
300
Featured
See All Featured
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
38
3k
Organizational Design Perspectives: An Ontology of Organizational Design Elements
kimpetersen
PRO
1
840
Skip the Path - Find Your Career Trail
mkilby
1
250
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
870
The Curious Case for Waylosing
cassininazir
1
560
Reality Check: Gamification 10 Years Later
codingconduct
0
2.3k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
2.1k
Fantastic passwords and where to find them - at NoRuKo
philnash
53
4k
[Rails World 2026] Durable orchestration on Rails: from continuation to workflow
palkan
1
510
Effective software design: The role of men in debugging patriarchy in IT @ Voxxed Days AMS
baasie
1
550
Utilizing Notion as your number one productivity tool
mfonobong
4
610
Jamie Indigo - Trashchat’s Guide to Black Boxes: Technical SEO Tactics for LLMs
techseoconnect
PRO
0
700
Transcript
!UTVSVCFF(.01FQBCP *OD )PTUJOH$BTVBM5BMLT ػցֶशͰαʔόͷ ෛՙঢ়ଶΛѲ͍ͨ͠
ࣗݾհ (.0ϖύϘגࣜձࣾ ϗεςΟϯάࣄۀ෦ ΠϯϑϥνʔϜ !UTVSVCFF
None
ࠓ͢͜ͱ wʮΠϯϑϥºσʔλαΠΤϯεʯʹ͍ͭͯ͜Μͳ͜ͱ Ͱ͖Δͱ໘നͦ͏ͩͳʔͱࢲ͕ߟ͍͑ͯΔ͜ͱ wࠓճαʔόࢹʹযΛͯͯ͠·͢
wΠϯϑϥͷݱʹʑେྔͷσʔλ͕ྲྀΕ͍ͯΔ wσʔλΛߴղ૾ͰऔಘɾੵͰ͖Δڥ͕͖͍ͬͯͯΔ ʢ1SPNFUIFVTɺ,BGLBͳͲʣ wσʔλੵ͢Δ͚ͩͰͳ͘׆༻͍ͨ͠ wੵͨ͠େྔͷσʔλʹػցֶशΛద༻Ͱ͖Εɺ৽ͨͳ ࣝൃݟʹܨ͕ΓՁΛͰ͖ΔͷͰͳ͍͔ എܠɿҰൠ
wϗεςΟϯάαʔόҟৗ͕ൃੜ͍͢͠ˍ੍ޚͮ͠Β͍ wߴूੵͷڞ༻αʔό wαʔό্Ͱಈ࡞͢ΔίϯςϯπΛཧͰ͖ͳ͍ wϢʔβαʔόΛબͳ͍ͨΊɺՄೳͳݶΓฏʹշదͳ αʔόڥΛఏڙ͍ͨ͠ എܠɿϨϯλϧαʔόʢ-PMJQPQ)FUFNMʣ
wϗεςΟϯάαʔόҟৗ͕ൃੜ͍͢͠ˍ੍ޚͮ͠Β͍ wߴूੵͷڞ༻αʔό wαʔό্Ͱಈ࡞͢ΔίϯςϯπΛཧͰ͖ͳ͍ wϢʔβαʔόΛબͳ͍ͨΊɺՄೳͳݶΓฏʹշదͳ αʔόڥΛఏڙ͍ͨ͠ എܠɿϨϯλϧαʔόʢ-PMJQPQ)FUFNMʣ αʔόͷঢ়ଶΛਫ਼៛ʹѲ੍ͯ͠ޚ͍ͨ͠
wϗεςΟϯάαʔόҟৗ͕ൃੜ͍͢͠ˍ੍ޚͮ͠Β͍ wߴूੵͷڞ༻αʔό wαʔό্Ͱಈ࡞͢ΔίϯςϯπΛཧͰ͖ͳ͍ wϢʔβαʔόΛબͳ͍ͨΊɺՄೳͳݶΓฏʹշదͳ αʔόڥΛఏڙ͍ͨ͠ എܠɿϨϯλϧαʔόʢ-PMJQPQ)FUFNMʣ αʔόͷঢ়ଶΛਫ਼៛ʹѲ੍ͯ͠ޚ͍ͨ͠ ػցֶशʹΑΔ Ξϓϩʔν͕༗ޮ
wαʔόͷϦιʔε༻ঢ়گϩάͳͲͷࢹରͷϝτϦ Ϋε͝ͱʹᮢΛઃఆ͠ɺͦͷᮢΛ্ճΔ߹ʹΞϥʔτ Λൃใ͢Δʮᮢϕʔεͷࢹʯ͕Ұൠత αʔόࢹͷݱঢ় $16༻ ࣌ؒ ᮢ ΞϥʔτΛൃใ
ݱঢ়ΛѲ্ͨ͠Ͱ ඞͣߟ͑ͳ͚ΕͳΒͳ͍ ͜ͱ͕͋Δ
ຊʹػցֶश͕ඞཁͳͷ͔ ʮ.BDIJOF-FBSOJOH5IF)JHI*OUFSFTU$SFEJU$BSEPG 5FDIOJDBM%FCUʯ %4DVMMFZFUBM (PPHMF wػցֶशΛγεςϜʹΈࠐΉͷେ͖ͳٕज़తෛ࠴Λ ๊͑ࠐΉϦεΫ͕͋Δ͜ͱΛೝࣝ͢Δ wจதͰ༷ʑͳϦεΫཁҼʹ͍ͭͯઆ໌͞Ε͍ͯΔ
ຊʹػցֶश͕ඞཁͳͷ͔ ʮ.BDIJOF-FBSOJOH5IF)JHI*OUFSFTU$SFEJU$BSEPG 5FDIOJDBM%FCUʯ %4DVMMFZFUBM (PPHMF wػցֶशΛγεςϜʹΈࠐΉͷେ͖ͳٕज़తෛ࠴Λ ๊͑ࠐΉϦεΫ͕͋Δ͜ͱΛೝࣝ͢Δ wจதͰ༷ʑͳϦεΫཁҼʹ͍ͭͯઆ໌͞Ε͍ͯΔ ػցֶशΛʮ͏ʯ͜ͱ͕తʹͳͬͯͳΒͳ͍
Θͳͯ͘ࡁΉͳΒΘͳ͍͕࠷ྑͷબ
ᮢϕʔεͷࢹͷݶք ࢹͷਫ਼Λ্͛ΔͨΊʹ໌ࣔతʹࣄલࣝΛೖΕͯ ϧʔϧΛ૿͍͔ͯ͘͠͠ͳ͍ ྫ͑ɺ ̍ฏͷ"͔࣌Β#࣌ͷؒͰɺ͔ͭαʔόΛϦϦʔεͯ͠ ͔Β$ϲ݄ະຬͷ$16༻͕%Λ͑ͨͱ͖ҟৗ ̎$16༻͕&ҎͰ͋Δͱ͖ʹϝϞϦ༻͕' Ҏ্ʹͳͬͨͱ͖ҟৗ
ᮢϕʔεͷࢹͷݶք ࢹͷਫ਼Λ্͛ΔͨΊʹ໌ࣔతʹࣄલࣝΛೖΕͯ ϧʔϧΛ૿͍͔ͯ͘͠͠ͳ͍ ྫ͑ɺ ̍ฏͷ"͔࣌Β#࣌ͷؒͰɺ͔ͭαʔόΛϦϦʔεͯ͠ ͔Β$ϲ݄ະຬͷ$16༻͕%Λ͑ͨͱ͖ҟৗ ̎$16༻͕&ҎͰ͋Δͱ͖ʹϝϞϦ༻͕' Ҏ্ʹͳͬͨͱ͖ҟৗ ਓ͕ؒ໌ࣔతʹࢦఆɾཧͰ͖Δϧʔϧͷʹݶք͕͋Δ JGจࠈʹ͍͍ؕͬͯ͘ɾɾ
ᮢϕʔεͷࢹͷݶք ࢹͷਫ਼Λ্͛ΔͨΊʹ໌ࣔతʹࣄલࣝΛೖΕͯ ϧʔϧΛ૿͍͔ͯ͘͠͠ͳ͍ ྫ͑ɺ ̍ฏͷ"͔࣌Β#࣌ͷؒͰɺ͔ͭαʔόΛϦϦʔεͯ͠ ͔Β$ϲ݄ະຬͷ$16༻͕%Λ͑ͨͱ͖ҟৗ ̎$16༻͕&ҎͰ͋Δͱ͖ʹϝϞϦ༻͕' Ҏ্ʹͳͬͨͱ͖ҟৗ ਓ͕ؒ໌ࣔతʹࢦఆɾཧͰ͖Δϧʔϧͷʹݶք͕͋Δ JGจࠈʹ͍͍ؕͬͯ͘ɾɾ
࣌ܥྻੑ
ᮢϕʔεͷࢹͷݶք ࢹͷਫ਼Λ্͛ΔͨΊʹ໌ࣔతʹࣄલࣝΛೖΕͯ ϧʔϧΛ૿͍͔ͯ͘͠͠ͳ͍ ྫ͑ɺ ̍ฏͷ"͔࣌Β#࣌ͷؒͰɺ͔ͭαʔόΛϦϦʔεͯ͠ ͔Β$ϲ݄ະຬͷ$16༻͕%Λ͑ͨͱ͖ҟৗ ̎$16༻͕&ҎͰ͋Δͱ͖ʹϝϞϦ༻͕' Ҏ্ʹͳͬͨͱ͖ҟৗ ਓ͕ؒ໌ࣔతʹࢦఆɾཧͰ͖Δϧʔϧͷʹݶք͕͋Δ JGจࠈʹ͍͍ؕͬͯ͘ɾɾ
࣌ܥྻੑ ଟ࣍ݩੑʢ૬ؔੑʣ
݁ہͲ͏͍͏ͱ͖ʹ ػցֶश͕͑Δͷʁ
wσʔλͷ࣌ܥྻੑΛߟྀ͍ͨ͠߹ w͜ͷ࣌ظͷ͜ͷ࣌ؒଳʹͦͷҟৗ͡Όͳ͍ʁ Έ͍ͨͳύλʔϯ wσʔλಉ࢜ͷ૬ؔଟ࣍ݩੑΛߟྀ͍ͨ͠߹ wͦͷͷ߹ͤҟৗ͡Όͳ͍ʁΈ͍ͨͳύλʔϯ ػցֶश͕༗ޮͳέʔε
wσʔλͷ࣌ܥྻੑΛߟྀ͍ͨ͠߹ w͜ͷ࣌ظͷ͜ͷ࣌ؒଳʹͦͷҟৗ͡Όͳ͍ʁ Έ͍ͨͳύλʔϯ wσʔλಉ࢜ͷ૬ؔଟ࣍ݩੑΛߟྀ͍ͨ͠߹ wͦͷͷ߹ͤҟৗ͡Όͳ͍ʁΈ͍ͨͳύλʔϯ ػցֶश͕༗ޮͳέʔε ͞Βʹͦͷ྆ํͷଟ࣍ݩ࣌ܥྻσʔλ͔Βͷࣝൃݟɺ ϧʔϧϕʔεͰ͘͠ɺػցֶशͷಘҙ
͡Ό͋Ͳ͏ͬͯػցֶशΛ ద༻͍ͯ͘͠ͷ͔ʁ
αʔόΛଟ࣍ݩ࣌ܥྻσʔλͱͯ͠ଊ͑ɺ ͦͷಛΛநग़͢ΔʢಛϕΫτϧԽʣ ಘΒΕͨಛ͔Βঢ়ଶΛਫ਼៛ʹѲ͢Δ ʢෛՙঢ়گͷѲɺҟৗ༧ଌͳͲʣ
·ͣಛϕΫτϧԽ
ಛϕΫτϧԽ ʮใਪનγεςϜೖɿߨٛεϥΠυʯΑΓҾ༻ IUUQTXXXTMJEFTIBSFOFU,FOUB0LVTT
ಛϕΫτϧԽ ʮใਪનγεςϜೖɿߨٛεϥΠυʯΑΓҾ༻ IUUQTXXXTMJEFTIBSFOFU,FOUB0LVTT αʔό ❓
αʔόͷಛϕΫτϧԽ αʔόͷঢ়ଶΛΑ͘දݱͨ͠ಛϕΫτϧͷઃܭ͕ॏཁ $16༻ ϝϞϦ༻ -" ɹɹɹ
ಛϕΫτϧ ن֨Խ ಛҟղ Χʔωϧؔ FUD ಛϕΫτϧͷઃܭࣗ༝͕ߴ͍ αʔό ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾ ɾɾɾ ࣌ؒ ଟ࣍ݩ࣌ܥྻσʔλ ن֨Խ ࣌ؒ
࠷ߴͷಛϕΫτϧ ͕ಘΒΕͨΒʜ
ಛϕΫτϧΛͬͨαʔόࢹ αʔόͷঢ়ଶΛදݱͨ͠ ಛϕΫτϧ ΞϧΰϦζϜͷબࣗ༝͕ߴ͍ ࣌ؒ 0OF$MBTT 47. ࠞ߹ Ϟσϧ ෦ۭؒ๏
σΟʔϓ ϥʔχϯά
IUUQTTQFBLFSEFDLDPNTVHJZBNBNBDLFSFMNFFUVQOVNCFS ࣄྫɿ.BDLFSFMʢגࣜձࣾͯͳʣ
͍ͯ͠ΔΞϧΰϦζϜ
࣌ܥྻΫϥελϦϯά IUUQTCMPHUTVSVCFFUFDIFOUSZ IUUQTCMPHUTVSVCFFUFDIFOUSZ ڭࢣͳֶ͠शͰ͋ΔΫϥελϦϯάΛ࣌ܥྻσʔλʹదԠ ͨ͠ͷ
ͳͥΫϥελϦϯάʁ ϗεςΟϯάαʔόͷಛ wಉ͡ϩʔϧʢׂʣͰΘΕ͍ͯΔαʔόͷ͕ଟ͍ ʢ-PMJQPQͩͱඦεέʔϧʣ wಉҰϩʔϧͰ͋Δ͕ɺαʔόຖʹಛ͕େ͖͘ҟͳΔ w࣌ؒଳʹΑͬͯෛՙঢ়ଶ͕େ͖͘ҟͳΔ ֎ΕݕมԽݕͳͲͷϝτϦΫεͷઈରΛ༻͍ ͨҟৗݕΑΓɺ૬ରతʹݟͯଞͱৼΔ͍͕ҟͳΔͷ ݕग़͢Δํ͕૬ੑ͕ྑͦ͞͏
࣌ܥྻΫϥελϦϯάͷద༻Πϝʔδ ಛϕΫτϧಉ࢜ͷྨࣅΛࢉग़͠ɺଞͱৼΔ͍͕ ҟͳΔαʔόΛ͋ͿΓग़͢ αʔόΛ্ۭؒͷͱͯ͠දݱͯ͠ ಉ࢜ͷڑʢྨࣅʣΛࢉग़ ूஂ͔ΒΕ͍ͯΔ ͷΛҟৗͱ͢Δ ࣌ؒ ͭͷʹͷαʔόͷ ଟ࣍ݩ࣌ܥྻσʔλͷ
ใ͕ೖ͍ͬͯΔΠϝʔδ
UTDMVTUFS࣌ܥྻΫϥελϦϯάύοέʔδ ಈత࣌ؒ৳ॖ๏ʢ%58ʣɾLNFEPJET๏Λ࣮
UTDMVTUFS࣌ܥྻΫϥελϦϯάϥΠϒϥϦ ࣍ݩআྨࣅࢉग़ͷख๏ͳͲɺಠཱͨ͠ෳͷॲཧ ͷΈ߹ΘͤΛࣗ༝ʹม͑ΒΕΔ IUUQTVNFYQFSUVNFEVNZpMFQVCMJDBUJPO@QEG
·ͱΊ wαʔό্Ͱಈ࡞͢Δίϯςϯπ͕ཧͰ͖ͣɺҟৗ੍͕ޚ͠ ͮΒ͍ϗεςΟϯάڥʹ͓͍ͯػցֶशΛ༻͍ͨαʔόࢹ ༗ޮͳͷͰͳ͍͔ wαʔόΛ࣌ܥྻଟ࣍ݩσʔλͱͯ͠ଊ͑ɺαʔόͷঢ়ଶΛΑ ͘දݱͨ͠ಛϕΫτϧΛઃܭ͢Δ͜ͱ͕ॏཁ wಛϕΫτϧΛͲ͏͏͔ʹଟ͘ͷબ͕͋ΓɺϗεςΟ ϯάαʔόʹ͓͍ͯ࣌ܥྻΫϥελϦϯά͕༗ޮͳͷͰͳ ͍͔ͱߟ͍͑ͯΔ w͍·ໝ͍ͯ͠Δ͜ͱΛ࣮ફ͍͖͍ͯͨ͠
͝ਗ਼ௌ͋Γ͕ͱ͏ ͍͟͝·ͨ͠ʂʂ