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
TensorFlow_First_Contact.pdf
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
JBClion
December 07, 2018
50
0
Share
TensorFlow_First_Contact.pdf
JBClion
December 07, 2018
More Decks by JBClion
See All by JBClion
A Chatbot experience - WeAreDevelopers 2018
jbclion
0
230
web ga webzueri
jbclion
0
200
Web-ML-Hamburg
jbclion
0
81
Web-ML-Berlin
jbclion
0
83
VanillaJS ML for Web Developers
jbclion
0
200
Microservices in Google App Engine
jbclion
1
88
Featured
See All Featured
Designing for Performance
lara
611
70k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
666
130k
We Are The Robots
honzajavorek
0
220
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
10k
職位にかかわらず全員がリーダーシップを発揮するチーム作り / Building a team where everyone can demonstrate leadership regardless of position
madoxten
62
54k
Reality Check: Gamification 10 Years Later
codingconduct
0
2.1k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
280
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
21
1.5k
Utilizing Notion as your number one productivity tool
mfonobong
4
300
Visual Storytelling: How to be a Superhuman Communicator
reverentgeek
2
530
Automating Front-end Workflow
addyosmani
1370
200k
Statistics for Hackers
jakevdp
799
230k
Transcript
TENSORFLOW FIRST CONTACT 12th April 2018 | by JB for
GDG Zürich
An open source software library for high performance numerical computation?
None
MACHINE LEARNING...
NEURAL NETWORK
Just one more can make it deep! DEEP NEURAL NETWORK
THIS is DEEEEEEP!!
NEURAL NETWORK WITH MULTIPLE HIDDEN LAYERS = DEEP NEURAL NETWORK
GET USED TO IT, MORTY. WE’RE IN UNIVERSE WHERE ARTISTIC TALENT DOES NOT EXIST. OH MAN, RICK THESE WHITE BACKGROUND ARE MAKING ME PRETTY UNCOMFORTABLE
What can we do with Deep Neural Networks?
What can we do with Deep Neural Networks?
None
None
TRAINING
That is a loooooooooot of work!!!
That is a loooooooooot of time!!!
That is a loooooooooot of effort!!!
I don’t have time! Is there a way to make
it faster!?
None
I see no dog...
bit.ly/TF-First LET’S DO IT!!