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
42
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
ML Session n°4
Adrien Couque
April 05, 2017
More Decks by Adrien Couque
See All by Adrien Couque
A roadmap to psychohistory
acq
0
110
ML Session n°8
acq
0
64
ML Session n°7
acq
0
26
ML Session n°6
acq
0
43
ML Session n°5
acq
0
64
ML Session n°3
acq
0
110
ML Session n°2
acq
1
100
ML Session n°1
acq
0
97
Intro to Machine Learning for Android developers
acq
0
200
Other Decks in Technology
See All in Technology
Model Studio CLI × Token Plan
maigo999
0
200
英語が話せなくてもKubeConスタッフに参加した話
yusuke427
0
1k
8bit CPU 2026
koba789
3
1.3k
Head First モブプログラミング / Head First Mobprogramming
takaking22
10
12k
Invisible to AI? Making TYPO3 Sites Quotable by AI Search Systems
wolfgangwagner
0
240
Software Supply Chain Attackからクラウド環境を守るためにできること
lhazy
2
290
AI開発に用いられるHPC技術について
gpuunite_official
0
190
FORENSIA: ローカルLLMフォレンジックハーネス
sumeshi
2
430
まちスペース®とデジタルツインと「まちづくり」
hiro_ogi
0
130
AI-DLC実践録_フルサイクル開発への挑戦
miyuc
0
320
Contract One Engineering Unit 紹介資料
sansan33
PRO
0
19k
AI時代に、人は何を、どう学ぶのか #pbl_pub / What and How Do We Learn in the AI Era?
takaking22
1
190
Featured
See All Featured
The Limits of Empathy - UXLibs8
cassininazir
1
610
SEO for Brand Visibility & Recognition
aleyda
0
4.7k
Site-Speed That Sticks
csswizardry
13
1.5k
Redefining SEO in the New Era of Traffic Generation
szymonslowik
1
390
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
28
3.6k
Tell your own story through comics
letsgokoyo
1
1k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
38
3k
Marketing to machines
jonoalderson
1
5.7k
Facilitating Awesome Meetings
lara
57
7.1k
We Are The Robots
honzajavorek
0
300
Tips & Tricks on How to Get Your First Job In Tech
honzajavorek
1
710
How to Build an AI Search Optimization Roadmap - Criteria and Steps to Take #SEOIRL
aleyda
1
2.1k
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