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
AI + JavaScript Rocks @ GDGDevFest UA 2018
Search
Asim Hussain
October 10, 2018
Technology
0
45
AI + JavaScript Rocks @ GDGDevFest UA 2018
Asim Hussain
October 10, 2018
Tweet
Share
More Decks by Asim Hussain
See All by Asim Hussain
JavaScript Saves The World - DotJS 2019
jawache
0
880
Saving the world, one line at a time [CodeLeaders Australia 2019]
jawache
0
68
YGLF_2019.pdf
jawache
1
120
How to hack a web app? WebConfAsia 2018
jawache
0
80
How to scale an SPA? @ AmsterdamJS 2018
jawache
0
24
How to hack an Angular app? - ngConf 2018
jawache
0
900
Getting started with node.js @ AngleBrackets 2018
jawache
1
170
How to hack an Angular app? @ ngVikings 2018
jawache
1
1.1k
How to hack a python app? @ PyCaribbean 2018
jawache
0
160
Other Decks in Technology
See All in Technology
コンテナセキュリティのためのLandlock入門
nullpo_head
2
320
Jetpack Composeで始めるServer Cache State
ogaclejapan
2
170
LINE Developersプロダクト(LIFF/LINE Login)におけるフロントエンド開発
lycorptech_jp
PRO
0
120
LINEヤフーのフロントエンド組織・体制の紹介【24年12月】
lycorp_recruit_jp
0
530
多領域インシデントマネジメントへの挑戦:ハードウェアとソフトウェアの融合が生む課題/Challenge to multidisciplinary incident management: Issues created by the fusion of hardware and software
bitkey
PRO
2
100
How to be an AWS Community Builder | 君もAWS Community Builderになろう!〜2024 冬 CB募集直前対策編?!〜
coosuke
PRO
2
2.8k
大幅アップデートされたRagas v0.2をキャッチアップ
os1ma
2
530
re:Invent をおうちで楽しんでみた ~CloudWatch のオブザーバビリティ機能がスゴい!/ Enjoyed AWS re:Invent from Home and CloudWatch Observability Feature is Amazing!
yuj1osm
0
120
kargoの魅力について伝える
magisystem0408
0
210
AI時代のデータセンターネットワーク
lycorptech_jp
PRO
1
280
Wantedly での Datadog 活用事例
bgpat
1
440
終了の危機にあった15年続くWebサービスを全力で存続させる - phpcon2024
yositosi
8
7.3k
Featured
See All Featured
Testing 201, or: Great Expectations
jmmastey
40
7.1k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
44
9.3k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
226
22k
Building Better People: How to give real-time feedback that sticks.
wjessup
365
19k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
26
1.9k
How to train your dragon (web standard)
notwaldorf
88
5.7k
VelocityConf: Rendering Performance Case Studies
addyosmani
326
24k
Making the Leap to Tech Lead
cromwellryan
133
9k
Adopting Sorbet at Scale
ufuk
73
9.1k
Optimising Largest Contentful Paint
csswizardry
33
3k
Keith and Marios Guide to Fast Websites
keithpitt
410
22k
The Pragmatic Product Professional
lauravandoore
32
6.3k
Transcript
None
How to AI in JS? Asim Hussain Developer Advocate Microsoft
AI JavaScript Rocks
Asim Hussain @jawache codecraft.tv microsoft.com
https://aka.ms/jawache-cda @jawache
@jawache
Asim Web Development Machine Learning This is @EleanorHaproff's slide
None
Opinion @jawache
TheMojifier™ @jawache
None
@jawache
Calculate Emotion @jawache
https://towardsdatascience.com/facial-keypoints-detection-deep-learning-737547f73515
Use an Artificial Neural Network @jawache
Artificial Neural Networks Axon Dendrites Axons Body @jawache
Artificial Neural Networks 1 23 8.6 -0.5 2.1 Activation Function
@jawache
Artificial Neural Networks 1 23 8.6 -0.5 2.1 x x
activation(...) = -11.5 = 18.06 7.01 !-> !-> } @jawache
Output 0 0 1 Input Artificial Neural Networks @jawache
Output 0 -1 1 Input Artificial Neural Networks TanH @jawache
Output 0 0 1 Input Artificial Neural Networks Relu @jawache
Artificial Neural Networks 1.1 4.2 0.3 4 12 93 3
@jawache
Artificial Neural Networks 1.1 4.2 0.3 4 12 93 3
- 8 = -5 @jawache
Artificial Neural Networks 1.1 4.2 0.3 4 12 93 3
- 8 = -5 @jawache
Artificial Neural Networks 0.1 9.2 0.2 4 12 93 8
@jawache
@jawache https://azure.microsoft.com/services/cognitive-services/face/
https:!//<region>.api.cognitive.microsoft.com/face/v1.0/detect { "url": "<path-to-image>" } @jawache
@jawache
Summary @jawache
• Neural Networks are incredibly powerful • Conceptually, they are
simple to understand @jawache Summary
TensorFlow, MobileNet & I'm fine @jawache
@jawache
@jawache
@jawache
TensorFlow.js @jawache
TensorFlow.js Train models Load pre-trained models @jawache
https://github.com/tensorflow/tfjs-models @jawache MobileNet
https://azure.microsoft.com/services/cognitive-services/computer-vision/ @jawache
https://codepen.io/sdras/full/jawPGa/ @jawache
@jawache https://twitter.com/ollee/status/930303340516216832
@jawache https://twitter.com/FrontendNE/status/930120267992616960
@jawache https://twitter.com/chrispiecom/status/930407801402347520
Summary @jawache
• TensorFlow.js doesn't have any dependancies • MobileNet is a
simple way to analyse images • Azure Computer Vision API ❤ @jawache Summary
Image2Image @jawache
DEMO @jawache https://zaidalyafeai.github.io/pix2pix/cats.html
@jawache Generator Discriminator ✅ ❌
@jawache Generator Discriminator ✅ ❌
@jawache Generator Discriminator ✅ ✅
@jawache
@jawache
@jawache
@jawache https://github.com/NVIDIA/vid2vid
@jawache https://github.com/NVIDIA/vid2vid
@jawache https://github.com/NVIDIA/vid2vid
https://github.com/NVIDIA/vid2vid @jawache
@jawache https://github.com/hanzhanggit/StackGAN
Summary @jawache
• GANs learn to generate new images • They take
a lot of compute to train • But the generator model can be run in the browser @jawache Summary
@jawache aka.ms/mojifier
@jawache themojifer.com
Tero Parviainen creative.ai Music and AI in the Browser with
TensorFlow.js and Magenta.js
Thoughts @jawache
Asim Hussain @jawache codecraft.tv microsoft.com