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
機械学習のための数学 〜微分・偏微分の計算, 勾配降下法(最急降下法)〜
Search
kkeeth
December 15, 2016
Science
2
2.8k
機械学習のための数学 〜微分・偏微分の計算, 勾配降下法(最急降下法)〜
機械学習を学ぶ上で必要となる「微分・偏微分」と、単純パーセプトロンを学ぶ上で必要となる「勾配降下法(最急降下法)」を理解し、実際に計算ができることが目標です。
kkeeth
December 15, 2016
Tweet
Share
More Decks by kkeeth
See All by kkeeth
The history of Javascript frameworks: changes in front-end design philosophy
clown0082
2
99
Visually experience the beauty of mathematics with p5.js
clown0082
1
2.7k
Rediscover the joy of coding with Creative Coding
clown0082
0
1.3k
全員が意思決定する会社で開発者体験や生産性を見る大変さについて
clown0082
0
550
JavaScript × Mathematics go to Digital Art
clown0082
1
310
In-house study group at YUMEMI
clown0082
0
160
Playing Ionic Logo by p5.js
clown0082
0
210
Skills that employers recommend students to acquire
clown0082
1
260
Walking through the source code of an OSS Library(ESLint))
clown0082
0
350
Other Decks in Science
See All in Science
MoveItを使った産業用ロボット向け動作作成方法の紹介 / Introduction to creating motion for industrial robots using MoveIt
ry0_ka
0
160
拡散モデルの原理紹介
brainpadpr
3
4.8k
Boil Order
uni_of_nomi
0
120
All-in-One Bioinformatics Platform Realized with Snowflake ~ From In Silico Drug Discovery, Disease Variant Analysis, to Single-Cell RNA-seq
ktatsuya
0
230
Mechanistic Interpretability の紹介
sohtakahashi
0
350
AI科学の何が“哲学”の問題になるのか ~問いマッピングの試み~
rmaruy
1
2.3k
ウェーブレットおきもち講座
aikiriao
1
790
インフラだけではない MLOps の話 @事例でわかるMLOps 機械学習の成果をスケールさせる処方箋 発売記念
icoxfog417
2
580
Celebrate UTIG: Staff and Student Awards 2024
utig
0
460
拡散モデルの概要 −§2. スコアベースモデルについて−
nearme_tech
PRO
0
570
How were Quaternion discovered
kinakomoti321
2
1.1k
ベイズ最適化をゼロから
brainpadpr
2
810
Featured
See All Featured
Fantastic passwords and where to find them - at NoRuKo
philnash
50
2.9k
Mobile First: as difficult as doing things right
swwweet
222
8.9k
We Have a Design System, Now What?
morganepeng
50
7.2k
jQuery: Nuts, Bolts and Bling
dougneiner
61
7.5k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
250
21k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
28
2k
Automating Front-end Workflow
addyosmani
1366
200k
StorybookのUI Testing Handbookを読んだ
zakiyama
27
5.3k
What’s in a name? Adding method to the madness
productmarketing
PRO
22
3.1k
A Tale of Four Properties
chriscoyier
156
23k
The Cult of Friendly URLs
andyhume
78
6k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
0
99
Transcript
Copyright© 2016 Leprachaun Corp. All Rights Reserved 機械学習のための数学 微分・偏微分の計算, 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分とは
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数?導関数?
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数とは
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数とは What’s !?
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数(補足) この値を 極限という
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数(具体例)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数(具体例) 因数分解!
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数(具体例)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数(具体例) 約分して
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数(具体例)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数(具体例)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数(具体例)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数(具体例) この値は何を 意味する?
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数の意味
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数の意味
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数の意味
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数の意味 微分係数の値と一致
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分係数の意味 微分係数は, 点aにおける 接線の傾きを表す!
Copyright© 2016 Leprachaun Corp. All Rights Reserved 導関数とは
Copyright© 2016 Leprachaun Corp. All Rights Reserved 導関数(求め方)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 導関数(具体例)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分練習問題
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分練習問題(回答)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分練習問題(回答)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 微分練習問題(回答)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 関数の四則演算に対する微分
Copyright© 2016 Leprachaun Corp. All Rights Reserved 関数の四則演算に対する微分
Copyright© 2016 Leprachaun Corp. All Rights Reserved 関数の四則演算に対する微分(具体例)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 偏微分
Copyright© 2016 Leprachaun Corp. All Rights Reserved 偏…微分?
Copyright© 2016 Leprachaun Corp. All Rights Reserved そう, 偏った微分.
Copyright© 2016 Leprachaun Corp. All Rights Reserved 偏微分とは
Copyright© 2016 Leprachaun Corp. All Rights Reserved 偏微分(具体例) 実際に計算してみよう!
Copyright© 2016 Leprachaun Corp. All Rights Reserved 偏微分(具体例)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved もちろんこいつ! 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 勾配降下法(最急降下法) これはグラフ全体が分かって いるから分かる!
Copyright© 2016 Leprachaun Corp. All Rights Reserved じゃあ、全体が分からない ときはどうする? 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved こいつに 注目! こいつに注目! 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved この点での 傾きは正! この点での 傾きは負!
勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved この点は 負の方向 に! 勾配降下法(最急降下法)
この点は 正の方向に!
Copyright© 2016 Leprachaun Corp. All Rights Reserved この点は 負の方向に! この点は 正の方向に!
勾配降下法(最急降下法) 緑の点を傾きに比例した 距離だけ動かしてみる
Copyright© 2016 Leprachaun Corp. All Rights Reserved 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 勾配降下法(最急降下法)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 勾配降下法(最急降下法) この勾配降下法には 弱点がある…(次回)
Copyright© 2016 Leprachaun Corp. All Rights Reserved 以上です。
Copyright© 2016 Leprachaun Corp. All Rights Reserved ありがとうございました!
Copyright© 2016 Leprachaun Corp. All Rights Reserved 付録
Copyright© 2016 Leprachaun Corp. All Rights Reserved 関数の極限の厳密な定義
Copyright© 2016 Leprachaun Corp. All Rights Reserved 導関数一覧
Copyright© 2016 Leprachaun Corp. All Rights Reserved 合成関数の微分