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
18
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
31
ML Session n°8
acq
0
46
ML Session n°7
acq
0
14
ML Session n°6
acq
0
18
ML Session n°5
acq
0
40
ML Session n°3
acq
0
34
ML Session n°2
acq
1
30
ML Session n°1
acq
0
23
Intro to Machine Learning for Android developers
acq
0
170
Other Decks in Technology
See All in Technology
アクセシビリティを考慮したUI/CSSフレームワーク・ライブラリ選定
yajihum
2
980
生産性向上チームの紹介
cybozuinsideout
PRO
1
850
AWS認定資格を取得したので、初めてマネコンを触った時を振り返ってみた。
ainatsuptr
2
100
ワールドカフェI /チューターを改良する / World Café I and Improving the Tutors
ks91
PRO
0
110
Janus
bkuhlmann
1
490
データベース02: データベースの概念
trycycle
0
140
4年前、あるじゃん老害エンジニアLT合戦に登壇、米国西海岸コンピュータ歴史博物館体験記の続編
toshi_atsumi
0
220
自動生成を活用した、運用保守コストを抑える Error/Alert/Runbook の一元集約管理 / Centralized management of Error/Alert/Runbook to minimize operational costs using automated code generation
biwashi
12
2.3k
開発生産性大幅アップ!Postman VS Code拡張機能
nagix
2
350
「手動オペレーションに定評がある」と言われた私が心がけていること / phpcon_odawara2024
blue_goheimochi
2
370
アクセス制御にまつわる改善 / Improving access control
itkq
0
490
20240418_Google ColabにLLMが搭載されたようなのでPython x データ分析の勉強方法を考えてみる
doradora09
0
120
Featured
See All Featured
Unsuck your backbone
ammeep
663
57k
10 Git Anti Patterns You Should be Aware of
lemiorhan
647
58k
Automating Front-end Workflow
addyosmani
1355
200k
A Tale of Four Properties
chriscoyier
150
22k
YesSQL, Process and Tooling at Scale
rocio
163
13k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
243
20k
Rails Girls Zürich Keynote
gr2m
91
13k
For a Future-Friendly Web
brad_frost
171
8.9k
The Brand Is Dead. Long Live the Brand.
mthomps
48
28k
Building a Scalable Design System with Sketch
lauravandoore
455
32k
Statistics for Hackers
jakevdp
789
220k
A Philosophy of Restraint
colly
196
16k
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