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
ML Session n°4
Search
Adrien Couque
April 05, 2017
Technology
0
29
ML Session n°4
Adrien Couque
April 05, 2017
Tweet
Share
More Decks by Adrien Couque
See All by Adrien Couque
A roadmap to psychohistory
acq
0
80
ML Session n°8
acq
0
58
ML Session n°7
acq
0
21
ML Session n°6
acq
0
29
ML Session n°5
acq
0
51
ML Session n°3
acq
0
86
ML Session n°2
acq
1
77
ML Session n°1
acq
0
75
Intro to Machine Learning for Android developers
acq
0
190
Other Decks in Technology
See All in Technology
カンファレンスに託児サポートがあるということ / Having Childcare Support at Conferences
nobu09
1
430
能登半島災害現場エンジニアクロストーク 【JAWS FESTA 2025 in 金沢】
ditccsugii
0
160
Why Governance Matters: The Key to Reducing Risk Without Slowing Down
sarahjwells
0
120
Goに育てられ開発者向けセキュリティ事業を立ち上げた僕が今向き合う、AI × セキュリティの最前線 / Go Conference 2025
flatt_security
0
360
実装で解き明かす並行処理の歴史
zozotech
PRO
1
630
いまさら聞けない ABテスト入門
skmr2348
1
220
Where will it converge?
ibknadedeji
0
200
自動テストのコストと向き合ってみた
qa
0
200
[Keynote] What do you need to know about DevEx in 2025
salaboy
0
120
ZOZOのAI活用実践〜社内基盤からサービス応用まで〜
zozotech
PRO
0
220
from Sakichi Toyoda to Agile
kawaguti
PRO
1
100
生成AIとM5Stack / M5 Japan Tour 2025 Autumn 東京
you
PRO
0
240
Featured
See All Featured
The World Runs on Bad Software
bkeepers
PRO
71
11k
Speed Design
sergeychernyshev
32
1.1k
Agile that works and the tools we love
rasmusluckow
331
21k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
35
3.2k
Code Reviewing Like a Champion
maltzj
525
40k
VelocityConf: Rendering Performance Case Studies
addyosmani
332
24k
Visualization
eitanlees
148
16k
Why You Should Never Use an ORM
jnunemaker
PRO
59
9.6k
Automating Front-end Workflow
addyosmani
1371
200k
Designing for Performance
lara
610
69k
GraphQLの誤解/rethinking-graphql
sonatard
73
11k
Building Applications with DynamoDB
mza
96
6.7k
Transcript
ML: regularization and neural networks March 2017
Recap
Recap: linear regression
Recap: polynomial regression
Recap: gradient descent
Regularization
Normalization Goal : have all features be equivalent (in size)
Rescaling : Standardization :
Regularization : goal
Regularization Before : Now : Forces values to stay low
Neural networks
Demo: Tensorflow Playground
Biological neuron
Artificial neuron: Perceptron
Teaching a neuron
Artifical neuron : activation function
Most common activation functions Identity Sigmoid Tanh ReLU
Teaching a neuron
Demo: simple network, but the hard way (92%)
Demo: simple network, but the hard way (92%)
Artificial neuron -> Artificial neural network
Artificial neuron -> Artificial neural network
Teaching a neural net
Demo: Tensorflow Playground
Demo: layered network, still the hard way (97%)
Questions? March 2017