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
機械学習を用いた大相撲千秋楽の勝敗予想 / sumo prediction by machin...
Search
Shotaro Ishihara
August 24, 2019
Technology
2.2k
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
850
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
130
[ACL 2026 Demo] Fast-MIA: Efficient and Scalable Membership Inference for LLMs
upura
0
95
Fast-MIA: Efficient and Scalable Membership Inference for LLMs
upura
0
68
JAPAN AI CUP Prediction Tutorial
upura
2
1.3k
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
430
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
780
Quantifying Memorization in Continual Pre-training with Japanese General or Industry-Specific Corpora
upura
1
130
JOAI2025講評 / joai2025-review
upura
0
1.8k
Other Decks in Technology
See All in Technology
トークンマネジメントでAIにとって働きやすい環境を実現する
hikaruegashira
0
120
自宅NWにISR4331を導入してみた話
okaits
0
110
システム思考で問題に対処する
yussak
0
350
【GCC2026】鉄拳8でのVFX開発事例
bandainamcostudios
PRO
0
120
まちスペース®とデジタルツインと「まちづくり」
hiro_ogi
0
130
名刺メーカーDevグループ 紹介資料
sansan33
PRO
0
1.2k
同じWAFが、攻撃の“形”は弾く── 正当な“形”の不正は通す
kuroneko13
0
250
モダンフロントエンド 開発研修
recruitengineers
PRO
4
830
Flutter × BLE Centralを自前Pluginで実装する設計パターン - MethodChannel / EventChannelで作る双方向ブリッジの実践 / Building Custom Flutter BLE Central Plugins: Bidirectional Bridging with Method & Event Channels
bitkey
PRO
0
170
Digitization部 紹介資料
sansan33
PRO
2
7.7k
Android skills に学ぶ
kokiko
0
120
Software Supply Chain Attackからクラウド環境を守るためにできること
lhazy
2
280
Featured
See All Featured
BBQ
matthewcrist
89
10k
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
650
SEO in 2025: How to Prepare for the Future of Search
ipullrank
3
3.8k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
659
62k
The Curious Case for Waylosing
cassininazir
1
460
Designing for humans not robots
tammielis
254
26k
SERP Conf. Vienna - Web Accessibility: Optimizing for Inclusivity and SEO
sarafernandez
2
1.6k
The untapped power of vector embeddings
frankvandijk
2
1.8k
GraphQLとの向き合い方2022年版
quramy
50
15k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
12
1.3k
Odyssey Design
rkendrick25
PRO
2
770
Building Better People: How to give real-time feedback that sticks.
wjessup
370
20k
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