Upgrade to Pro — share decks privately, control downloads, hide ads and more …

ML Session n°4

Sponsored · Ship Features Fearlessly Turn features on and off without deploys. Used by thousands of Ruby developers. →
Avatar for Adrien Couque Adrien Couque
April 05, 2017
Technology
40
0

ML Session n°4

Avatar for Adrien Couque

Adrien Couque

April 05, 2017

More Decks by Adrien Couque

See All by Adrien Couque
A roadmap to psychohistory
Avatar for Adrien Couque acq
0
110
ML Session n°8
Avatar for Adrien Couque acq
0
64
ML Session n°7
Avatar for Adrien Couque acq
0
26
ML Session n°6
Avatar for Adrien Couque acq
0
41
ML Session n°5
Avatar for Adrien Couque acq
0
64
ML Session n°3
Avatar for Adrien Couque acq
0
110
ML Session n°2
Avatar for Adrien Couque acq
1
97
ML Session n°1
Avatar for Adrien Couque acq
0
96
Intro to Machine Learning for Android developers
Avatar for Adrien Couque acq
0
200

Other Decks in Technology

See All in Technology
AI研修(Day2)【MIXI 26新卒技術研修】
Avatar for MIXI ENGINEERS mixi_engineers
PRO
2
1.4k
データ活用研修 データマネジメント【MIXI 26新卒技術研修】
Avatar for MIXI ENGINEERS mixi_engineers
PRO
4
750
データエンジニアこそ組織のオントロジーに向き合うべき — 問いに答えるAIから、事業を動かすAIへ
Avatar for harry gappy50
4
1.2k
大 AI 時代におけるC# の事情 ～ぶっちゃけトークを交えながら～
Avatar for neno nenonaninu
1
520
探索・可視化・自動化を一本化 Amazon Quickでデータ活用スピードを上げる方法
Avatar for こーへい koheiyoshikawa
0
230
文字起こし基盤の信頼性
Avatar for abnoumaru abnoumaru
0
150
数値で見る Microsoft MVP 〜Spec Kit と GitHub Copilot Agent で作るデータ可視化ダッシュボード〜
Avatar for yutakaosada yutakaosada
0
160
AI エージェント時代のデジタルアイデンティティ
Avatar for Naohiro Fujie fujie
1
1.1k
なぜMIXIはゼロトラスト基盤として クラウドフレアを選んだのか - Cloudflare Peer Point SASE User Voices
Avatar for MIXI ENGINEERS mixi_engineers
PRO
2
130
AIエージェントの知識表現と推論に なぜグラフが使われるのか - 記号的AIの復権とニューラルAIとの統合
Avatar for Yohei Onishi yohei1126
1
190
1台から試せる！Edge IoTを使った位置情報の活用設計【SORACOM Discovery 2026】
Avatar for SORACOM（ソラコム） soracom
PRO
0
100
AIとハーネスで育てるトランスコンパイラ / 20260722 Yasushi Katayama
Avatar for SHIFT EVOLVE shift_evolve
PRO
4
1.1k

Featured

See All Featured
XXLCSS - How to scale CSS and keep your sanity
Avatar for Zaharenia Atzitzikaki sugarenia
249
1.3M
YesSQL, Process and Tooling at Scale
Avatar for Rocio Delgado rocio
174
15k
Navigating Team Friction
Avatar for Lara Hogan lara
192
16k
Rails Girls Zürich Keynote
Avatar for Gregor Martynus gr2m
96
14k
Practical Orchestrator
Avatar for Shlomi Noach shlominoach
191
11k
Noah Learner - AI + Me: how we built a GSC Bulk Export data pipeline
Avatar for Tech SEO Connect techseoconnect
PRO
0
340
Practical Tips for Bootstrapping Information Extraction Pipelines
Avatar for Matthew Honnibal honnibal
25
2k
First, design no harm
Avatar for Per Axbom axbom
PRO
2
1.2k
How to train your dragon (web standard)
Avatar for Monica Dinculescu notwaldorf
97
6.7k
A designer walks into a library…
Avatar for Paul Jervis Heath pauljervisheath
211
24k
Evolving SEO for Evolving Search Engines
Avatar for Ryan Jones ryanjones
0
250
Rebuilding a faster, lazier Slack
Avatar for samanthasiow samanthasiow
85
9.6k

Transcript

  1. ML: regularization and neural networks March 2017

  2. Recap

  3. Recap: linear regression

  4. Recap: polynomial regression

  5. Recap: gradient descent

  6. Regularization

  7. Normalization Goal : have all features be equivalent (in size)

    Rescaling : Standardization :

  8. Regularization : goal

  9. Regularization Before : Now : Forces values to stay low

  10. Neural networks

  11. Demo: Tensorflow Playground

  12. Biological neuron

  13. Artificial neuron: Perceptron

  14. Teaching a neuron

  15. Artifical neuron : activation function

  16. Most common activation functions Identity Sigmoid Tanh ReLU

  17. Teaching a neuron

  18. Demo: simple network, but the hard way (92%)

  19. Demo: simple network, but the hard way (92%)

  20. Artificial neuron -> Artificial neural network

  21. Artificial neuron -> Artificial neural network

  22. Teaching a neural net

  23. Demo: Tensorflow Playground

  24. Demo: layered network, still the hard way (97%)

  25. Questions? March 2017