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
25
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
54
ML Session n°8
acq
0
53
ML Session n°7
acq
0
17
ML Session n°6
acq
0
25
ML Session n°5
acq
0
46
ML Session n°3
acq
0
70
ML Session n°2
acq
1
62
ML Session n°1
acq
0
59
Intro to Machine Learning for Android developers
acq
0
180
Other Decks in Technology
See All in Technology
DevOps文化を育むQA 〜カルチャーバブルを生み出す戦略〜 / 20250317 Atsushi Funahashi
shift_evolve
1
120
PostgreSQL Unconference #52 pg_tde
nori_shinoda
1
250
AIエージェント完全に理解した
segavvy
4
330
AIエージェントキャッチアップと論文リサーチ
os1ma
6
1.3k
「ラベルにとらわれない」エンジニアでいること/Be an engineer beyond labels
kaonavi
0
220
SREが実現する開発者体験の革新
sansantech
PRO
0
100
どっちの API SHOW?SharePoint 開発における SharePoint REST API Microsoft Graph API の違い / Which API show? Differences between Microsoft Graph API and SharePoint REST API
karamem0
0
160
caching_sha2_passwordのはなし
boro1234
0
260
Agile TPIを活用した品質改善事例
tomasagi
0
490
3/26 クラウド食堂LT #2 GenU案件を通して学んだ教訓 登壇資料
ymae
1
230
一人QA時代が終わり、 QAチームが立ち上がった話
ma_cho29
0
300
スケールアップ企業のQA組織のバリューを最大限に引き出すための取り組み
tarappo
4
1.1k
Featured
See All Featured
StorybookのUI Testing Handbookを読んだ
zakiyama
28
5.6k
How to train your dragon (web standard)
notwaldorf
91
5.9k
GraphQLの誤解/rethinking-graphql
sonatard
70
10k
What’s in a name? Adding method to the madness
productmarketing
PRO
22
3.4k
jQuery: Nuts, Bolts and Bling
dougneiner
63
7.7k
RailsConf 2023
tenderlove
29
1k
Unsuck your backbone
ammeep
670
57k
How STYLIGHT went responsive
nonsquared
99
5.4k
Side Projects
sachag
452
42k
Intergalactic Javascript Robots from Outer Space
tanoku
270
27k
Why Our Code Smells
bkeepers
PRO
336
57k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
29
2k
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