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
機械学習ことはじめ
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Shotaro Ishihara
April 26, 2019
Technology
130
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
機械学習ことはじめ
Shotaro Ishihara
April 26, 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
初海外で注意すべきこと12選!!!安全快適なre:invent生活にするために
yuuuuuuu168
1
180
日本語に強いオープンな大規模言語モデル「LLM-jp」
odashi
5
1.2k
会社説明資料
persolserverworks
0
9.8k
DevelopersIO 2026 知識の地図を描く ─ オントロジーとは何か?
ishikawa_satoru
1
1.7k
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
600
コンテナ運用におけるネットワーク・コンテナコストの削減方法/How to Reduce Network and Container Costs in Container Operations
masakiokuda
1
280
Post AI時代のリファクタリング実践記 / Refactoring in the post AI era
kaminashi
1
270
『SAR衛星データ解析入門』のご紹介とその応用
syuchimu
0
120
触りたくないデータに、どう触るか AI時代のRBACアクセスガバナンス
ivry_presentationmaterials
0
270
Tofu-Controller lightning talk @ Containerday 2026
gionn
0
120
Getting Started with Google Antigravity
glaforge
0
320
DWH の限界突破! AI エージェント向け爆速リアルタイムデータ基盤 ClickHouse
jozono
1
490
Featured
See All Featured
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
31
3.4k
Rails Girls Zürich Keynote
gr2m
96
14k
WENDY [Excerpt]
tessaabrams
14
40k
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.5k
How GitHub (no longer) Works
holman
316
150k
Leading Effective Engineering Teams in the AI Era
addyosmani
9
2.7k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
570
Rebuilding a faster, lazier Slack
samanthasiow
85
9.7k
The Curse of the Amulet
leimatthew05
3
16k
Mobile First: as difficult as doing things right
swwweet
225
10k
Bioeconomy Workshop: Dr. Julius Ecuru, Opportunities for a Bioeconomy in West Africa
akademiya2063
PRO
1
410
Money Talks: Using Revenue to Get Sh*t Done
nikkihalliwell
0
520
Transcript
ػցֶश͜ͱ͡Ί ݄
ຊͷ • ͡Ίʹ • ػցֶशͱ • ڭࢣ͋Γֶश • ڭࢣͳֶ͠श
• ڧԽֶश
֮͑ͯؼͬͯ΄͍͜͠ͱ • "* ػցֶश σΟʔϓϥʔχϯάͷؔੑ • ػցֶशͷྨͱͦΕͧΕͷಛ • ڭࢣ͋Γֶश
ڭࢣͳֶ͠श ڧԽֶश • େΛѲͯ͠ɺ"*ͬΆ͍Λฉ͍ͨ࣌ʹʮػց ֶश͔ͳʁʯʮ۩ମతʹͲΜͳΈͩΖ͏ʁʯ ͱ͔ߟ͑ΒΕΕे
ຊͷ • ͡Ίʹ • ػցֶशͱ • ڭࢣ͋Γֶश • ڭࢣͳֶ͠श
• ڧԽֶश
ਓೳ <>ਓೳֶձਓೳͬͯԿʁ IUUQTXXXBJHBLLBJPSKQXIBUTBJ"*XIBUTIUNM • େ͖͘ྲྀʢ͜ͷྨࣗମʹ͕ٞ͋Δʣ ਓؒͷೳͦͷͷΛͭػցΛ࡞Ζ͏ͱ͢Δཱ
ਓ͕ؒೳΛͬͯ͢Δ͜ͱΛػցʹͤ͞Α͏ͱ͢ Δཱ • ࣮ࡍͷݚڀ΄ͱΜͲޙऀͷཱʢͳͷʹ͔ͬͯ Β͔ͣલऀͷҙຯͰ૽ཱ͗ͯΔք۾͕͋Δʣ
ػցֶश • ίϯϐϡʔλʹώτͷΑ͏ͳֶशೳྗΛ֫ಘͤ͞ ΔͨΊͷٕज़ͷ૯শ • ਓೳ ∋ ػցֶश •
࠷ۙͷਓೳ ػցֶश <>ਿࢁক ʰΠϥετͰֶͿػցֶशʱ ߨஊࣾ
ػցֶशͷྨ • ֶशํ๏ʹґͬͯେ͖͘ྨ • ڭࢣ͋Γֶश • ڭࢣͳֶ͠श • ڧԽֶश
<>ਿࢁক ʰΠϥετͰֶͿػցֶशʱ ߨஊࣾ
ຊͷ • ͡Ίʹ • ػցֶशͱ • ڭࢣ͋Γֶश • ڭࢣͳֶ͠श
• ڧԽֶश
ڭࢣ͋Γֶश • ίϯϐϡʔλʹͱ͑ͷରΛ͍͔ͭ͘ڭ͑Δ ͜ͱʹΑΓɼڭΘ͍ͬͯͳ͍ʹਖ਼͘͠ճ Ͱ͖Δ൚ԽೳྗΛίϯϐϡʔλʹ֫ಘͤ͞Δ <>ਿࢁক ʰΠϥετͰֶͿػցֶशʱ ߨஊࣾ
ڭࢣ͋Γֶशͷ۩ମྫ • खॻ͖จࣈೝࣝɼԻೝࣝɼը૾ೝࣝɼ໎ϝʔ ϧͷࣗಈྨͳͲ <>ਿࢁক ʰΠϥετͰֶͿػցֶशʱ ߨஊࣾ
ֶशɾ༧ଌͷΞϧΰϦζϜ • ͍Ζ͍ΖͳΞϧΰϦζϜ͕։ൃ͞Ε͍ͯΔ • ͦͷҰ͕ͭɺσΟʔϓϥʔχϯά
ຊͷ • ͡Ίʹ • ػցֶशͱ • ڭࢣ͋Γֶश • ڭࢣͳֶ͠श
• ڧԽֶश
ڭࢣͳֶ͠श • ͑ͷ͔͍ͬͯͳ͍σʔλͷू߹͔Βɺ༗ӹͳ ࣝΛ֫ಘ͠Α͏ͱ͢Δ • ੈͷதʹਖ਼ղϥϕϧͷͳ͍σʔλͷํ͕ѹత ʹଟ͍ <>ਿࢁক ʰΠϥετͰֶͿػցֶशʱ
ߨஊࣾ
ڭࢣͳֶ͠शͷ۩ମྫ • ΫϥελϦϯάҟৗݕ <>ਿࢁক ʰΠϥετͰֶͿػցֶशʱ ߨஊࣾ
ຊͷ • ͡Ίʹ • ػցֶशͱ • ڭࢣ͋Γֶश • ڭࢣͳֶ͠श
• ڧԽֶश
ڧԽֶश • ڭࢣ͋Γֶशͱಉ͘͡൚ԽੑೳΛίϯϐϡʔλʹ ֫ಘͤ͞Δ͜ͱ͕ඪ • ͑Λڭ͑ΔΘΓʹɼ༧ଌͨ͑͠ͷྑ͞ ΛධՁ • ධՁ͕࠷ߴ·ΔΑ͏ʹֶश͢Δ
<>ਿࢁক ʰΠϥετͰֶͿػցֶशʱ ߨஊࣾ
ڧԽֶशͷ۩ମྫ • ϩϘοτͷࣗಈ੍ޚɼίϯϐϡʔλήʔϜͳͲ • ໌֬ʹਖ਼ղσʔλ͕༩͑ͮΒ͍߹ʹ༻͍ΒΕΔ • ྫɿғޟͰʮͱ͋Δ൫໘ͰԿΛଧͭͷ͕ਖ਼ղʯ͔ ݴ͍Δͷ͍͠ ˠͱ͋ΔखΛଧͬͨΒউͬͨෛ͚ͨͱ͍͏ධՁ
Λͱʹֶश͍ͤͯ͘͜͞ͱͰ͖ͦ͏
֮͑ͯؼͬͯ΄͍͜͠ͱ • "* ػցֶश σΟʔϓϥʔχϯάͷؔੑ • ػցֶशͷྨͱͦΕͧΕͷಛ • ڭࢣ͋Γֶश
ڭࢣͳֶ͠श ڧԽֶश • େΛѲͯ͠ɺ"*ͬΆ͍Λฉ͍ͨ࣌ʹʮػց ֶश͔ͳʁʯʮ۩ମతʹͲΜͳΈͩΖ͏ʁʯ ͱ͔ߟ͑ΒΕΕे