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
SantaFeTrail
Search
TAKAMASA Saichi
October 10, 2014
Programming
160
2
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
SantaFeTrail
esysLTかどこかで発表した遺伝的プログラミングに関するスライド
TAKAMASA Saichi
October 10, 2014
More Decks by TAKAMASA Saichi
See All by TAKAMASA Saichi
メトリクス可視化から始める Rails ウェブサーバーのチューニング- Kaigi On Rails 2021
s4ichi
3
2k
Cookpad 5day service dev internship 2017 teamC
s4ichi
0
950
Region based memory management for mini ML
s4ichi
2
220
主専攻実験(春) 巡回セールスマン問題
s4ichi
0
870
Other Decks in Programming
See All in Programming
Enforcing Your Architecture with Unit Tests in the AI Era (Swift Connection X)
steliosf
PRO
1
150
AI時代のシニアエンジニアとは
yosuke_furukawa
PRO
15
11k
PyConTW 2026 - AI Coding 不只是工具升級, 區域醫院醫療資訊系統協作開發與資訊團隊轉型實踐
cclai999
0
240
當我們開始不讀 Code - AI Agent 時代,Code Review 與 Clean Code 還剩下什麼?
jame2408
1
360
全ての永続トークンを、生まれる前に消し去りたい!
sylph01
3
1.7k
プロジェクトコードをキレイキレイしよう!暗黙的な参照を読み解く静的解析
ostk0069
0
210
Modernizing iOS Apps
seyfoyun
0
150
[DroidKnights 2026] Workflow AX: From Auto-Documented Policies to E2E Testing
raeminkang
0
540
学びを記事・スライド・Xへ高速展開する― AI-assisted Learning Loopで回すコンテンツ生成術
ochtum
0
200
Distance field of Julia set
kinakomoti321
0
300
GraphQL の onError と Nullability のこれから
quramy
0
210
動画プレイヤーはなぜカクつくのか 〜Flutterのレンダリングとネイティブの境界を解剖する〜
naruogram
0
330
Featured
See All Featured
AI Search: Implications for SEO and How to Move Forward - #ShenzhenSEOConference
aleyda
1
1.4k
Designing for Timeless Needs
cassininazir
1
550
A brief & incomplete history of UX Design for the World Wide Web: 1989–2019
jct
2
560
How to Think Like a Performance Engineer
csswizardry
28
2.9k
How to make the Groovebox
asonas
2
2.5k
Docker and Python
trallard
47
4.3k
4 Signs Your Business is Dying
shpigford
187
23k
Getting science done with accelerated Python computing platforms
jacobtomlinson
2
570
The untapped power of vector embeddings
frankvandijk
2
2k
HDC tutorial
michielstock
2
1k
ラッコキーワード サービス紹介資料
rakko
5
5.7M
Avoiding the “Bad Training, Faster” Trap in the Age of AI
tmiket
1
300
Transcript
←͍ͭ͜ͷ coins14 @everysick
ඈͼೖΓͰ͢
ඈͼೖΓͰ͢ ਅ໘ͳ͠·͢
Ҩతϓϩάϥϛϯά
ҧ͍ ίϯϐϡʔλαΠΤϯεدΓ จܥͰΘ͔ΔΑ͏ʹؤுΓ·͢
GP(Ҩతϓϩάϥϛϯά) ͬͯͳΜͧ
GP(Ҩతϓϩάϥϛϯά) ͬͯͳΜͧ AIͬΆ͍͚Ͳҧ͏Կ͔ ϓϩάϥϜʹ੍ͱ͔ΞϧΰϦζϜΛ༩͑ͯ ੜͷਐԽͬΆ͘γϛϡϨʔτ͢Δͷ
(‘ω’)ɻ˓(???????????????????????)
GP(Ҩతϓϩάϥϛϯά) ͬͯͳΜͧ ʮ͜Μͳ෩ʹਐԽͯ͘͠ΕཔΉʯ ϓϩάϥϜʮ͑͑Ͱ͆ʯ
࣮ͷ
ࠜ અ ࢬ ༿ ߏ ྫ
։࢝ ऴྃ ॳظੈੜ ద߹ܭࢉ ऴྃ ఆ ੈҾ͖ܧ͗ ݁Ռදࣔ ॳظੈͷߏ ཚΛͬͯੜ
ަ伹ɾಥવมҟɾબ ΛϓϩάϥϜͰදݱ͠ ͦͷॲཧΛՃ͑Δ ٻΊͨղ͕ͲΕ͚ͩ ۙࣅ͍ͯ͠Δ͔ܭࢉ
Santa Fe Trail ٜͷਐԽΛγϛϡϨʔτ N*NͷϚεʹٜͱ㕒͕ஔ औಘͨ͠㕒͕ద߹ ٜ 㕒
Santa Fe Trail ٜ400ͷΤωϧΪʔΛ࣋ͭ ٜ͔Βݟͯલํʹ͔͠ਐΊͳ͍ ࠨӈʹ90ํస͢Δ͜ͱ͕Ͱ͖Δ Ҡಈ,ճసʹ͖ͭΤωϧΪʔΛ1ফඅ͢Δ
1 – Santa Fe TrailͷϓϩάϥϜ࡞ • બΞϧΰϦζϜ • બग़ͨ͠ݸମΛมԽΛՃ͑ͣ࣍ੈʹՃ •
ݸମΛͦͷ··Ҩͤ͞Δํ๏ • ࠓճͷنଇ༰ • ֤ݸମΛۉʹҨ͍ͤͨ͞ બ͢ΔݸମΛཚͰܾఆ
1 – Santa Fe TrailͷϓϩάϥϜ࡞ • ަ伹ΞϧΰϦζϜ • ҙͷ2ݸମΛΈ߹Θͤɺ৽ͨͳݸମΛੜ •
ߏͷઅಉ࢜Λަ͢ΔͳͲͷख๏ • Ұަ伹ΞϧΰϦζϜ ݸମA ݸମB
1 – Santa Fe TrailͷϓϩάϥϜ࡞ • ಥવมҟΞϧΰϦζϜ • ҙͷ1ݸମΛબग़͢Δ •
ݸମʹϥϯμϜͰੜͨ͠ߏΛΈࠐΉ • ΞϧΰϦζϜ֓ཁ ϥϯμϜͰ࡞ΒΕͨߏ બग़͞Εͨݸମ
2 -ϓϩάϥϜΛ࣮ͬͯࡍʹ݁ՌΛܭଌ 㕒ɹɹ ɹ89ݸ ελʔτɹɹࠨ্ ΤωϧΪʔɹ400
2 -ϓϩάϥϜΛ࣮ͬͯࡍʹ݁ՌΛܭଌ ϓϩάϥϜॳظঢ়ଶͰͷܭଌ݁Ռ 0 22.5 45 67.5 90 0 10
20 30 40 50 60 70 80 90 100 औಘͨ͠㕒 ੈ
͑ɺେͨ͜͠ͱͳ͘Ͷʁ
2 -ϓϩάϥϜΛ࣮ͬͯࡍʹ݁ՌΛܭଌ ϓϩάϥϜॳظঢ়ଶͰͷܭଌ݁Ռ 0 22.5 45 67.5 90 0 10
20 30 40 50 60 70 80 90 100 औಘͨ͠㕒 ੈ
3 -Ҿ͖ܧ͗ΞϧΰϦζϜΛมߋ݁͠ՌͷมԽΛܭଌ • બ • ࠷ྑબΞϧΰϦζϜ • ੈத࠷ద߹ͷߴ͍ݸମΛ݁Ռ • ղ͕ภΓ͕ͪ
• ΤϦʔτબΞϧΰϦζϜ • ݸମΛద߹ॱͰιʔτ্͠ҐNݸબͿ • Nݸ͔ΒϥϯμϜͰબͨ͠ݸମΛ݁Ռ
• ద߹ܭࢉ • ࠓ·ͰͷΞϧΰϦζϜ • औಘͨ͠㕒ͷΛద߹ • ৽ΞϧΰϦζϜ • جຊऔಘͨ͠ΞΠςϜ
• ແବͳಈ͖͝ͱʹجຊ͔ΒఆϚΠφε • ࠓճ2ͭϚΠφεΛઃஔ 3 -Ҿ͖ܧ͗ΞϧΰϦζϜΛมߋ݁͠ՌͷมԽΛܭଌ
3 -Ҿ͖ܧ͗ΞϧΰϦζϜΛมߋ݁͠ՌͷมԽΛܭଌ ΞϧΰϦζϜվྑޙͷܭଌ݁Ռ औಘͨ͠㕒 0 22.5 45 67.5 90 ੈ
0 10 20 30 40 50 60 70 80 90 100
៉ྷʹͳͬͨ✌('ω'✌ )
3 -Ҿ͖ܧ͗ΞϧΰϦζϜΛมߋ݁͠ՌͷมԽΛܭଌ ΞϧΰϦζϜվྑޙͷܭଌ݁Ռ औಘͨ͠㕒 0 22.5 45 67.5 90 ੈ
0 10 20 30 40 50 60 70 80 90 100
4 -ύϥϝʔλΛௐ͠࠷ྑͷݸମΛબग़ 1. ੈ 2. ݸମ 3. ަ伹ཱ֬ 4. ಥવมҟཱ֬
5. બཱ֬ 6. બΞϧΰϦζϜ 500[ੈ] 100[ඖ] 89% 10% 1% ΤϦʔτબ
4 -ύϥϝʔλΛௐ͠࠷ྑͷݸମΛબग़ ࠷ऴܭଌ݁Ռ औಘͨ͠㕒 0 22.5 45 67.5 90 ੈ
0 50 100 150 200 250 300 350 400 450 500
தʹશճऩͱ͔
࣮ࡍָ͍͠ ࣮͍ܰ(300ߦఔ)
͓ΘΓ