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
機械学習を用いた大相撲千秋楽の勝敗予想 / sumo prediction by machin...
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Shotaro Ishihara
August 24, 2019
Technology
2.3k
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
機械学習を用いた大相撲千秋楽の勝敗予想 / sumo prediction by machine learning
Sports Analyst Meetup #4 (
https://spoana.connpass.com/event/138392/
) での発表資料。
Shotaro Ishihara
August 24, 2019
More Decks by Shotaro Ishihara
See All by Shotaro Ishihara
Agent 時代の Kaggle 展望 / kaggle-in-the-agentic-era
upura
1
1.4k
大規模言語モデルは誰を覚えているか / Who Do Large Language Models Memorize?
upura
0
220
[ACL 2026 Demo] Fast-MIA: Efficient and Scalable Membership Inference for LLMs
upura
0
150
Fast-MIA: Efficient and Scalable Membership Inference for LLMs
upura
0
100
JAPAN AI CUP Prediction Tutorial
upura
2
1.4k
情報技術の社会実装に向けた応用と課題:ニュースメディアの事例から / appmech-jsce 2025
upura
0
460
日本語新聞記事を用いた大規模言語モデルの暗記定量化 / LLMC2025
upura
0
840
Quantifying Memorization in Continual Pre-training with Japanese General or Industry-Specific Corpora
upura
1
150
JOAI2025講評 / joai2025-review
upura
0
1.9k
Other Decks in Technology
See All in Technology
日本語に強いオープンな大規模言語モデル「LLM-jp」
odashi
5
1.1k
Browser Spec: Testing Hotwire with Ruby
takahashim
1
130
JAWS-UGグッズ職人仕事の流儀
kentapapa
0
120
AIがコードを書く時代に、エンジニアは何で自分の価値を証明するのか / In an era where AI writes code how do engineers prove their value
carta_engineering
3
1.1k
Conditional PED-ANOVA: Hyperparameter Importance in Hierarchical & Dynamic Search Spaces
pfn
PRO
0
140
自作バイナリを動かす「入口」8選
puhitaku
2
1.3k
AI × アーキテクト 第1・2章|生成AIの課題とアーキテクトの素養
daidaidai
0
170
大型犬好きによるPugの紹介
yamanoku
1
160
継続的なAIコスト最適化
bgpat
1
340
ストレスなくAIと付き合いたい!こんなときどうしてる?
namiki64
3
560
実践!Cloud Run ハンズオン!! / Cloud Run handson
y0hgi
2
280
Rustuna: Rustによる高速なOptuna実装
pfn
PRO
0
190
Featured
See All Featured
The Power of CSS Pseudo Elements
geoffreycrofte
82
6.6k
GitHub's CSS Performance
jonrohan
1033
470k
Organizational Design Perspectives: An Ontology of Organizational Design Elements
kimpetersen
PRO
1
850
The Cost Of JavaScript in 2023
addyosmani
55
10k
How to train your dragon (web standard)
notwaldorf
96
6.9k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
128
56k
Dominate Local Search Results - an insider guide to GBP, reviews, and Local SEO
greggifford
PRO
0
370
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.5k
The SEO Collaboration Effect
kristinabergwall1
1
590
The AI Search Optimization Roadmap by Aleyda Solis
aleyda
2
6.3k
The World Runs on Bad Software
bkeepers
PRO
72
12k
Prompt Engineering for Job Search
mfonobong
0
520
Transcript
ػցֶशΛ༻͍ͨ େ૬ઍळָͷউഊ༧ V !VQVSB "VHUI 4QPSUT"OBMZTU.FFUVQ
V ͷඋ • େ૬ͷσʔλऩूʮ4VNP3FGFSFODFʯ͕ศར • ʲՄࢹԽฤʳػցֶशΛ༻͍ͨେ૬ઍळָͷউഊ༧ • ʲϕϯνϚʔΫฤʳػցֶशΛ༻͍ͨେ૬ઍळָͷউ ഊ༧ •
ʲಛྔͷՃฤʳػցֶशΛ༻͍ͨେ૬ઍळָͷউ ഊ༧ (JU)VC • IUUQTHJUIVCDPNVQVSBTVNPQSFEJDUPS ϦϯΫू
࣍ • എܠˍత • σʔλͷऔಘ • ػցֶशϞσϧͷ࡞ • ಛྔͷՃ
• ݁ˍࠓޙͷల
• V !VQVSB • ࣄۀձࣾͷσʔλαΠΤϯςΟετ • TQPBOBӡӦ • ΘΜͺ͘૬໊ݹॴϕετ
࿈ଓ • ,BHHMF.BTUFS "U$PEFS ਫ ࣗݾհ
• ૬ͷσʔλΛ༻͍ͯɺػցֶशͰ ༧ଌϞσϧΛߏஙͰ͖ͳ͍͔ʁ • ૬ͷྗ࢜ใͰͳ͘ɺউͪෛ͚ ͷ࣌ܥྻใ͔Β༧ଌͯ͠Έ͍ͨ • ˞झຯͳͷͰશͳख๏υϦϒϯ ૬
º ,BHHMF
উͪෛ͚ͷ࣌ܥྻใ ˓˔˔˔˓ ˓˔˓˔˔ ˔˓˔˔ʁ ˔˓˓˓˓ ˔˔˓˔˓ ˓˔˔˓ʁ
࣍ • എܠˍత • σʔλͷऔಘ • ػցֶशϞσϧͷ࡞ • ಛྔͷՃ
• ݁ˍࠓޙͷల
• IUUQTVNPECTVNPHBNFTEF • TQPBOB Ͱͬͨ • ૬ͷ֤छσʔλ͕ཧ͞Ε͍ͯΔ • ྗ࢜ •
൪ • औΓΈ ͳͲ 4VNP3FGFSFODF
• 1ZUIPOͰඵ͝ͱʹॴͷσʔλ ΛऔಘɾՃͯ͠DTWͰอଘ • ʙͷσʔλ औಘ
• ྗ໊࢜ • ʙͷউഊ • ઍळָͷରઓྗ࢜ • ॴʢZZZZNNʣ • ઍळָͷউഊʢతมʣ
σʔλ߲
σʔλͷՄࢹԽ
• উഊͷ߹ͷউ͕ʢউഊ উഊͷ߹ʹൺͯʣߴ͍ • ·Ͱʹʙউ͍ͯ͠Δ ߹উ͕ΑΓߴ͍ • ˞ʮീඦʯͷٞΛ͢Δʹ ѻ͍ͬͯΔใྔ͕গͳ͗͢Δ
ߟ
࣍ • എܠˍత • σʔλͷऔಘ • ػցֶशϞσϧͷ࡞ • ಛྔͷՃ
• ݁ˍࠓޙͷల
σʔλͷׂ
• ྗ໊࢜ • ʙͷউഊ • ऴྃ࣌ͷউͪ • ઍळָͷରઓྗ࢜ • ॴʢZZZZNNʣ
• ઍळָͷউഊʢతมʣ ಛྔɾతม
• -JHIU(#.ʢ,BHHMFͰఆ൪ʣ • ܾఆΛେྔʹ࡞Δྨث • ಛྔ͕গͳ͍ͷΛҙࣝͯ͠ɺϋΠ ύʔύϥϝʔλΛखಈͰௐͨ͠ ػցֶशΞϧΰϦζϜ
• $7είΞɺ"6$ • UFTUɺ"6$ "$$ $7UFTUͷྨੑೳ
࣍ • എܠˍత • σʔλͷऔಘ • ػցֶशϞσϧͷ࡞ • ಛྔͷՃ
• ݁ˍࠓޙͷల
• ྗ໊࢜ • ʙͷউഊ • ·Ͱͷউͪ • ରઓྗ࢜ͷ·Ͱͷউͪ • ઍळָͷରઓྗ࢜
• ॴʢZZZZNNʣ • ઍळָͷউഊʢతมʣ ಛྔɾతม
• $7είΞɺ"6$ • UFTUɺ"6$ ɺ"$$ $7UFTUͷྨੑೳ
• ʮ·Ͱͷ࿈উɾ࿈ഊʯ $7UFTUͷྨੑೳͱʹඍ૿ • ͦͷଞͷ࣌ܥྻಛΛ lUTGSFTIzͰ େྔʹੜʢݸऑʣ͠ݸ࠾༻ ˠ$7UFTUͷྨੑೳ͕վળͤͣ ૣʑʹߦ͖٧·Δɾɾɾ
IUUQTUTGSFTISFBEUIFEPDTJPFOMBUFTU
࣍ • എܠˍత • σʔλͷऔಘ • ػցֶशϞσϧͷ࡞ • ಛྔͷՃ
• ݁ˍࠓޙͷల
• ػցֶशΛ༻͍ͯɺେ૬ઍळָͷ উഊΛ༧ͨ͠ • -JHIU(#.ϕʔεͰಛྔΛ૿͠ ͍ͯ͘ํ๏ʹݶք͕͋Γͦ͏ • ˞ͦͦ͜ͷใͰ༧Ͱ͖Δ͔ ୭ʹ͔Βͳ͍
݁
• ผͷػցֶशϞσϧΛࢼ͢ • উͪෛ͚ͷʮʯͷྲྀΕΛ 3//ʹೖΕΔ͜ͱͰɺௐࢠͷΛ ଊ͑ΒΕΔʁ • ࣍ճҎ߱ɺ·ͨൃද͠·͢ ࠓޙͷల