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
0
30

ML Session n°4

Avatar for Adrien Couque

Adrien Couque

April 05, 2017
Tweet

More Decks by Adrien Couque

See All by Adrien Couque
A roadmap to psychohistory
Avatar for Adrien Couque acq
0
91
ML Session n°8
Avatar for Adrien Couque acq
0
59
ML Session n°7
Avatar for Adrien Couque acq
0
24
ML Session n°6
Avatar for Adrien Couque acq
0
31
ML Session n°5
Avatar for Adrien Couque acq
0
55
ML Session n°3
Avatar for Adrien Couque acq
0
94
ML Session n°2
Avatar for Adrien Couque acq
1
84
ML Session n°1
Avatar for Adrien Couque acq
0
84
Intro to Machine Learning for Android developers
Avatar for Adrien Couque acq
0
190

Other Decks in Technology

See All in Technology
ClickHouseはどのように大規模データを活用したAIエージェントを全社展開しているのか
Avatar for Miki Matsumoto mikimatsumoto
0
220
OpenShiftでllm-dを動かそう！
Avatar for jpishikawa jpishikawa
0
100
10Xにおける品質保証活動の全体像と改善 #no_more_wait_for_test
Avatar for nihonbuson nihonbuson
PRO
2
240
今日から始める Amazon Bedrock AgentCore
Avatar for Har1101 har1101
4
410
Amazon Bedrock Knowledge Basesチャンキング解説！
Avatar for 野口碧生 aoinoguchi
0
140
Kiro IDEのドキュメントを全部読んだので地味だけどちょっと嬉しい機能を紹介する
Avatar for khmoryz khmoryz
0
180
Agile Leadership Summit Keynote 2026
Avatar for seki at druby.org m_seki
1
590
【Oracle Cloud ウェビナー】[Oracle AI Database + AWS] Oracle Database@AWSで広がるクラウドの新たな選択肢とAI時代のデータ戦略
Avatar for oracle4engineer oracle4engineer
PRO
2
140
プロダクト成長を支える開発基盤とスケールに伴う課題
Avatar for yuu26 yuu26
4
1.3k
Webhook best practices for rock solid and resilient deployments
Avatar for Guillaume Laforge glaforge
1
280
AIと新時代を切り拓く。これからのSREとメルカリIBISの挑戦
Avatar for ktykogm 0gm
0
890
We Built for Predictability; The Workloads Didn’t Care
Avatar for Michael Stahnke stahnma
0
140

Featured

See All Featured
The Success of Rails: Ensuring Growth for the Next 100 Years
Avatar for Eileen M. Uchitelle eileencodes
47
7.9k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
Avatar for Michelle Schulp Hunt marktimemedia
31
2.7k
Build The Right Thing And Hit Your Dates
Avatar for Maggie C. maggiecrowley
38
3k
Dealing with People You Can't Stand - Big Design 2015
Avatar for Cassini Nazir cassininazir
367
27k
How to Get Subject Matter Experts Bought In and Actively Contributing to SEO & PR Initiatives.
Avatar for Liv Day livdayseo
0
64
Testing 201, or: Great Expectations
Avatar for Joseph Mastey jmmastey
46
8k
How to audit for AI Accessibility on your Front & Back End
Avatar for davetheseo davetheseo
0
180
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
Avatar for David Carrasco davidcarrasco
1
51
What's in a price? How to price your products and services
Avatar for Michael Herold michaelherold
247
13k
Building Applications with DynamoDB
Avatar for Matt Wood mza
96
6.9k
Groundhog Day: Seeking Process in Gaming for Health
Avatar for Sebastian Deterding codingconduct
0
92
jQuery: Nuts, Bolts and Bling
Avatar for Doug Neiner dougneiner
65
8.4k

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