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
pillow-mosaic-art-nyumon
Search
nikkie
January 16, 2018
Programming
1
1.4k
pillow-mosaic-art-nyumon
Python入門者の集い#6 発表スライド
https://python-nyumon.connpass.com/event/71516/
nikkie
January 16, 2018
Tweet
Share
More Decks by nikkie
See All by nikkie
AIエージェントとは(UB Tech vol.21)
ftnext
0
190
sphinx-new-tab-link (2023/11 #guidomeetup)
ftnext
0
340
ChatGPT Prompt Engineering for Developers 受講体験記
ftnext
3
2.5k
Zuziさん、私、リーダーにあんまり向いてないと思うんです
ftnext
1
750
begin-pandas
ftnext
0
390
call-cvapi-with-python
ftnext
1
410
Other Decks in Programming
See All in Programming
メタプログラミングで実現する「コードを仕様にする」仕組み/nikkei-tech-talk43
nikkei_engineer_recruiting
0
200
nuget-server - あなたが必要だったNuGetサーバー
kekyo
PRO
0
280
野球解説AI Agentを開発してみた - 2026/02/27 LayerX社内LT会資料
shinyorke
PRO
0
350
AIコードレビューの導入・運用と AI駆動開発における「AI4QA」の取り組みについて
hagevvashi
0
500
守る「だけ」の優しいEMを抜けて、 事業とチームを両方見る視点を身につけた話
maroon8021
3
1.1k
Docコメントで始める簡単ガードレール
keisukeikeda
1
130
Understanding Apache Lucene - More than just full-text search
spinscale
0
130
AHC061解説
shun_pi
0
400
AI 開発合宿を通して得た学び
niftycorp
PRO
0
150
ふつうの Rubyist、ちいさなデバイス、大きな一年
bash0c7
0
1.1k
GC言語のWasm化とComponent Modelサポートの実践と課題 - Scalaの場合
tanishiking
0
120
SourceGeneratorのマーカー属性問題について
htkym
0
200
Featured
See All Featured
It's Worth the Effort
3n
188
29k
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
0
180
Un-Boring Meetings
codingconduct
0
230
Crafting Experiences
bethany
1
89
Odyssey Design
rkendrick25
PRO
2
550
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
3.7k
Principles of Awesome APIs and How to Build Them.
keavy
128
17k
What's in a price? How to price your products and services
michaelherold
247
13k
Intergalactic Javascript Robots from Outer Space
tanoku
273
27k
Testing 201, or: Great Expectations
jmmastey
46
8.1k
Design of three-dimensional binary manipulators for pick-and-place task avoiding obstacles (IECON2024)
konakalab
0
380
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
270
Transcript
1JMMPXͰ ϞβΠΫΞʔτ 1ZUIPOೖऀͷू͍ OJLLJF
ιϑτΣΞΤϯδχΞ OJLLJFʢʹ͖ͬʔʣ ݄͔ΒػցֶशҊ݅ ʢ1)1ఔʣ ʢ˞ػցֶशະܦݧʣ
IUUQTUXJUUFSDPNGUOFYU OJLLJF!GUOFYU IUUQTHJUIVCDPNGUOFYU IUUQOJLLJFGUOFYUIBUFOBCMPHDPN IUUQTRJJUBDPNGUOFYU
*-07&"/*.& OJLLJF!GUOFYU
࣭ɾࢦఠ͓͍ͪͯ͠·͢ IUUQNPWJFBOJNFFVQIPDPNTQFDJBMJDPOFVQI@JDPOQOH
1JMMPXͰ ϞβΠΫΞʔτ ܦҢ ϞβΠΫΞʔτͱʁ ϩδοΫ ՝ ·ͱΊ
1JMMPXͰ ϞβΠΫΞʔτ ܦҢ ϞβΠΫΞʔτͱʁ ϩδοΫ ՝ ·ͱΊ
ळ
ۀͰ࣮͢Δػձ͕ͳ͍ɻɻ IUUQNPWJFBOJNFFVQIPDPNTQFDJBMJDPOFVQI@JDPOQOH
Θͨ͠ɺ1ZUIPO͕͖ͩΜʂ IUUQTXXXZPVUVCFDPNXBUDI WTB3[S'BQBT
IUUQTXXXPSFJMMZDPKQCPPLT
None
ϞβΠΫΞʔτ࡞ͬͯΈ͍ͨ 1JMMPXͰը૾ૢ࡞͕Ͱ͖Δʂ 1JMMPXͰϞβΠΫΞʔτ࡞Ζ͏
1JMMPXͰ ϞβΠΫΞʔτ ܦҢ ϞβΠΫΞʔτͱʁ ϩδοΫ ՝ ·ͱΊ
OJLLJFࡱӨ
͍ۙͮͯݟΔͱখ͞ͳը૾ͷدͤूΊ ϞβΠΫΞʔτ ΕͯݟΔͱຕͷେ͖ͳը૾
͍ۙͮͯݟΔͱখ͞ͳը૾ͷدͤूΊ ϞβΠΫΞʔτ ΕͯݟΔͱຕͷେ͖ͳը૾ Ҏ߱ͷઆ໌Ͱૉࡐը૾ͱݺͼ·͢ Ҏ߱ͷઆ໌Ͱରը૾ͱݺͼ·͢
ରը૾ IUUQNPWJFBOJNFFVQIPDPNTQFDJBMJDPOFVQI@JDPOQOH
ૉࡐը૾ʢຕʣ IUUQUWBOJNFFVQIPDPNTQFDJBM
࡞ͬͯΈͨ
1JMMPXͰ ϞβΠΫΞʔτ ܦҢ ϞβΠΫΞʔτͱʁ ϩδοΫ ՝ ·ͱΊ
ରը૾Λ֨ࢠঢ়ʹׂ େ·͔ʹݴ͑ ৭͕Ұ൪͍ۙૉࡐը૾Λॖখͯ͠ ׂ͞ΕͨྖҬΛஔ͖͑
ରը૾Λ֨ࢠঢ়ʹׂ ˞࣮ࡍͬͱࡉ͔͍֨ࢠͰ͢
৭͕͍ۙૉࡐը૾Ͱஔ͖͑ ˞࣮ࡍछͷૉࡐը૾͔Βબͼ·͢
ରը૾ͷ֤ྖҬΛҰͭͷ৭Ͱදͤ͞Δ ৭ͷۙ͞ΛൺΔͨΊʹ ૉࡐը૾ͦΕͧΕҰͭͷ৭Ͱදͤ͞Δ
ฏۉ ը૾ͷ৭ͷදͷͤ͞ํ தԝ ࠷ස
ฏۉɿը૾ͷ৭ 3 ( # ͷฏۉ ը૾ͷ৭ͷදͷͤ͞ํ தԝ ࠷ස 1*-*NBHF4UBU4UBU NFBO
ฏۉɿը૾ͷ৭ 3 ( # ͷฏۉ ը૾ͷ৭ͷදͷͤ͞ํ தԝɿը૾ͷ৭Λେ͖͍ॱʹ ࠷ස 1*-*NBHF4UBU4UBU NFBO
1*-*NBHF4UBU4UBU NFEJBO ɹฒସ͑ͨͱ͖ʹɺதԝʹདྷΔ৭
ฏۉɿը૾ͷ৭ 3 ( # ͷฏۉ ը૾ͷ৭ͷදͷͤ͞ํ தԝɿը૾ͷ৭Λେ͖͍ॱʹ ࠷සɿը૾ͰҰ൪ΘΕ͍ͯΔ৭ 1*-*NBHF4UBU4UBU NFBO
1*-*NBHF4UBU4UBU NFEJBO ɹฒସ͑ͨͱ͖ʹɺதԝʹདྷΔ৭ TUBUJTUJDTNPEF
ରը૾ ฏۉ தԝ ࠷ස
ૉࡐը૾ ฏۉ தԝ ࠷ස
ରը૾ͷ֤ྖҬΛҰͭͷ৭Ͱදͤ͞Δ ৭ͷۙ͞ΛൺΔͨΊʹ ૉࡐը૾ͦΕͧΕҰͭͷ৭Ͱදͤ͞Δ ྖҬΛද͢Δ৭ʹ Ұ൪͍ۙૉࡐը૾ΛબͿ
৭ 3 ( # Λ࣍ݩۭؒͷ࠲ඪͱݟͳ͠ɺ ৭ͷʮۙ͞ʯ ͭͷ৭ͷʮڑʯΛٻΊΔ ڑ࠷খͷૉࡐը૾Ͱஔ͖͑Δ
දͷΈ߹Θͤ ฏۉ தԝ ࠷ස ରը૾ͷྖҬ ฏۉͰද ૉࡐը૾ͷද
දͷΈ߹Θͤ ฏۉ தԝ ࠷ස ରը૾ͷྖҬ ฏۉͰද ૉࡐը૾ͷද
දͷΈ߹Θͤ ૉࡐը૾ฏۉͰද ฏۉ தԝ ࠷ස
දͷΈ߹Θͤ ૉࡐը૾ฏۉͰද ฏۉ தԝ ࠷ස
ରը૾ɺૉࡐը૾ͱʹ ฏۉͰදͤ͞ΔͱΑͦ͞͏
1JMMPXͰ ϞβΠΫΞʔτ ܦҢ ϞβΠΫΞʔτͱʁ ϩδοΫ ՝ ·ͱΊ
ฏۉΛ͏ͷ͕࠷ద͔ʁ ࢁੵ͢Δ*TTVFT ൚༻Խ OVNQZಋೖͯ͠ΈΔ -5४උͰࢄΒ͔ͬͨϦϙδτϦͷཧ
1JMMPXͰ ϞβΠΫΞʔτ ܦҢ ϞβΠΫΞʔτͱʁ ϩδοΫ ՝ ·ͱΊ
1JMMPX͚ͩͰϞβΠΫΞʔτ࡞ΕΔ 1JMMPXͰϞβΠΫΞʔτ ఆతͳද ʢ*NBHF *NBHF4UBUʣ ରը૾ɺૉࡐը૾ͱʹฏۉ
͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ QZIBDLSFUUZQZͷ͘͘ձΛத৺ʹ ϞβΠΫΞʔτϥΠϒσϞͰ͖·͢ɻ ͜͜·ͰਐΊ·ͨ͠ɻӡӦͷํʑʹײँͰ͢ɻ ڵຯ͋Δํɺ࠙ձͰ͓͕͚͍ͩ͘͞ɻ 4QFDJBM5IBOLTژΞχϝʔγϣϯ ࣭ɾࢦఠ͓͍ͪͯ͠·͢