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
YGLF_2019.pdf
Search
Asim Hussain
April 05, 2019
Technology
1
120
YGLF_2019.pdf
Asim Hussain
April 05, 2019
Tweet
Share
More Decks by Asim Hussain
See All by Asim Hussain
JavaScript Saves The World - DotJS 2019
jawache
0
860
Saving the world, one line at a time [CodeLeaders Australia 2019]
jawache
0
61
AI + JavaScript Rocks @ GDGDevFest UA 2018
jawache
0
44
How to hack a web app? WebConfAsia 2018
jawache
0
79
How to scale an SPA? @ AmsterdamJS 2018
jawache
0
20
How to hack an Angular app? - ngConf 2018
jawache
0
760
Getting started with node.js @ AngleBrackets 2018
jawache
1
170
How to hack an Angular app? @ ngVikings 2018
jawache
1
1k
How to hack a python app? @ PyCaribbean 2018
jawache
0
160
Other Decks in Technology
See All in Technology
.NETの非同期戦略とUnityとの相互運用
neuecc
2
2.4k
10分でわかるfreeeのQA
freee
0
230
今さら聞けない!? AWSの生成AIサービス Amazon Bedrock入門!
minorun365
PRO
11
2.3k
技術広報として2023年度に頑張ったこと / What we did well in FY2023 as a DevRel
pauli
5
460
複数の LLM モデルを扱う上で直面した辛みまとめ
kazuyaseki
1
230
大規模なアジャイル開発の現場と技術負債 / Technical Debt
yoshiitaka
20
4k
ビジネスロジックを「型」で表現するOOPのための関数型DDD / Functional And Type-Safe DDD for OOP
yuitosato
29
12k
GitHub最新情報キャッチアップ 2024年3月
dzeyelid
16
3.2k
やっていきテスト
k6s4i53rx
0
160
関数型DDDの理論と実践:「決定を遅らせる」を先につくり、 ビジネスの機動力と価値をあげる
knih
2
470
Autopsy of a Cascading Outage from a MySQL Crashing Bug
jfg956
0
200
LLM + RAG を使った SORACOM Support Bot の裏側の歴史
soracom
PRO
1
640
Featured
See All Featured
A better future with KSS
kneath
230
16k
How to Ace a Technical Interview
jacobian
272
22k
Web development in the modern age
philhawksworth
201
10k
Gamification - CAS2011
davidbonilla
76
4.5k
Product Roadmaps are Hard
iamctodd
43
9.6k
Facilitating Awesome Meetings
lara
39
5.5k
ParisWeb 2013: Learning to Love: Crash Course in Emotional UX Design
dotmariusz
101
6.6k
Bootstrapping a Software Product
garrettdimon
PRO
302
110k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
272
12k
Happy Clients
brianwarren
91
6.3k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
19
1.6k
Documentation Writing (for coders)
carmenintech
59
3.8k
Transcript
The Future of Machine Learning & JavaScript @jawache YGLF 2019
Asim Hussain @jawache codecraft.tv microsoft.com
https://aka.ms/jawache-cda @jawache
@jawache https://www.palinternship.com/
@jawache
Asim Web Development Machine Learning This is @EleanorHaproff's slide
None
@jawache
TheMojifier™ @jawache
None
@jawache themojifier.com
None
How to Calculate Emotion? @jawache
(1) Detect Facial Features @jawache
https://towardsdatascience.com/facial-keypoints-detection-deep-learning-737547f73515
(2) Use a Neural Network @jawache
Neural Networks Axon Dendrites Axons Body @jawache
1 23 8.6 -0.5 2.1 Activation Function @jawache Neural Networks
1 23 8.6 -0.5 2.1 x x activation(...) = -11.5
= 18.06 7.01 !-> !-> } @jawache Neural Networks
Output 0 0 1 Input @jawache Neural Networks
1.1 4.2 0.3 4 12 93 3 @jawache Neural Networks
1.1 4.2 0.3 4 12 93 @jawache 8 - 8
= -5 3 Neural Networks
1.1 4.2 0.3 4 12 93 @jawache - 8 =
-5 3 8 Neural Networks
0.1 9.2 0.2 4 12 93 @jawache 8 8 Neural
Networks
@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
@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
Asim Hussain @jawache codecraft.tv microsoft.com