Upgrade to Pro — share decks privately, control downloads, hide ads and more …

AI + JavaScript Rocks @ GDGDevFest UA 2018

Sponsored · Ship Features Fearlessly Turn features on and off without deploys. Used by thousands of Ruby developers. →
Avatar for Asim Hussain Asim Hussain
October 10, 2018
Technology
0
62

AI + JavaScript Rocks @ GDGDevFest UA 2018

Avatar for Asim Hussain

Asim Hussain

October 10, 2018
Tweet

More Decks by Asim Hussain

See All by Asim Hussain
JavaScript Saves The World - DotJS 2019
Avatar for Asim Hussain jawache
0
910
Saving the world, one line at a time [CodeLeaders Australia 2019]
Avatar for Asim Hussain jawache
0
87
YGLF_2019.pdf
Avatar for Asim Hussain jawache
1
160
How to hack a web app? WebConfAsia 2018
Avatar for Asim Hussain jawache
0
98
How to scale an SPA? @ AmsterdamJS 2018
Avatar for Asim Hussain jawache
0
37
How to hack an Angular app? - ngConf 2018
Avatar for Asim Hussain jawache
0
1k
Getting started with node.js @ AngleBrackets 2018
Avatar for Asim Hussain jawache
1
190
How to hack an Angular app? @ ngVikings 2018
Avatar for Asim Hussain jawache
1
1.1k
How to hack a python app? @ PyCaribbean 2018
Avatar for Asim Hussain jawache
0
180

Other Decks in Technology

See All in Technology
【Oracle Cloud ウェビナー】データ主権はクラウドで守れるのか？NTTデータ様のOracle Alloyで実現するソブリン対応クラウドの最適解
Avatar for oracle4engineer oracle4engineer
PRO
3
110
スケーリングを封じられたEC2を救いたい
Avatar for いのうえ senseofunity129
0
110
FlutterでPiP再生を実装した話
Avatar for 白井翔大 s9a17
0
210
【AWS】CloudTrail LakeとCloudWatch Logs Insightsの使い分け方針
Avatar for Yuma Tsurugasaki tsurunosd
0
120
Phase04_ターミナル基礎
Avatar for overflow ,Inc overflowinc
0
2.6k
タスク管理も1on1も、もう「管理」じゃない - KiroとBedrock AgentCoreで変わった“判断の仕事”
Avatar for Yusuke Shimizu yusukeshimizu
0
130
PostgreSQL 18のNOT ENFORCEDな制約とDEFERRABLEの関係
Avatar for Yasuo Honda yahonda
0
140
Sansanの認証基盤を支えるアーキテクチャとその振り返り
Avatar for SansanTech sansantech
PRO
1
110
私がよく使うMCPサーバー3選と社内で安全に活用する方法
Avatar for KintoTech_Dev kintotechdev
0
130
Phase06_ClaudeCode実践
Avatar for overflow ,Inc overflowinc
0
2.2k
「捨てる」を設計する
Avatar for kubell kubell_hr
0
420
来期の評価で変えようと思っていること 〜AI時代に変わること・変わらないこと〜
Avatar for estie | エスティ estie
0
110

Featured

See All Featured
Measuring Dark Social's Impact On Conversion and Attribution
Avatar for Stephen Akadiri stephenakadiri
1
160
The Illustrated Children's Guide to Kubernetes
Avatar for Chris Short chrisshort
51
52k
Odyssey Design
Avatar for Ryan Kendrick rkendrick25
PRO
2
560
brightonSEO & MeasureFest 2025 - Christian Goodrich - Winning strategies for Black Friday CRO & PPC
Avatar for Christian Goodrich cargoodrich
3
130
Why Your Marketing Sucks and What You Can Do About It - Sophie Logan
Avatar for Sophie Logan marketingsoph
0
120
It's Worth the Effort
Avatar for 3n 3n
188
29k
The MySQL Ecosystem @ GitHub 2015
Avatar for Sam Lambert samlambert
251
13k
Game over? The fight for quality and originality in the time of robots
Avatar for Wayne Barker wayneb77
1
150
Marketing Yourself as an Engineer | Alaka | Gurzu
Avatar for Gurzu gurzu
0
160
Un-Boring Meetings
Avatar for Sebastian Deterding codingconduct
0
240
Claude Code のすすめ
Avatar for schroneko schroneko
67
220k
Code Review Best Practice
Avatar for Trisha Gee trishagee
74
20k

Transcript

  1. None

  2. How to AI in JS? Asim Hussain Developer Advocate Microsoft

    AI JavaScript Rocks

  3. Asim Hussain @jawache codecraft.tv microsoft.com

  4. https://aka.ms/jawache-cda @jawache

  5. @jawache

  6. Asim Web Development Machine Learning This is @EleanorHaproff's slide

  7. None

  8. Opinion @jawache

  9. TheMojifier™ @jawache

  10. None

  11. @jawache

  12. Calculate Emotion @jawache

  13. https://towardsdatascience.com/facial-keypoints-detection-deep-learning-737547f73515

  14. Use an Artificial Neural Network @jawache

  15. Artificial Neural Networks Axon Dendrites Axons Body @jawache

  16. Artificial Neural Networks 1 23 8.6 -0.5 2.1 Activation Function

    @jawache

  17. Artificial Neural Networks 1 23 8.6 -0.5 2.1 x x

    activation(...) = -11.5 = 18.06 7.01 !-> !-> } @jawache

  18. Output 0 0 1 Input Artificial Neural Networks @jawache

  19. Output 0 -1 1 Input Artificial Neural Networks TanH @jawache

  20. Output 0 0 1 Input Artificial Neural Networks Relu @jawache

  21. Artificial Neural Networks 1.1 4.2 0.3 4 12 93 3

    @jawache

  22. Artificial Neural Networks 1.1 4.2 0.3 4 12 93 3

    - 8 = -5 @jawache

  23. Artificial Neural Networks 1.1 4.2 0.3 4 12 93 3

    - 8 = -5 @jawache

  24. Artificial Neural Networks 0.1 9.2 0.2 4 12 93 8

    @jawache

  25. @jawache https://azure.microsoft.com/services/cognitive-services/face/

  26. https:!//<region>.api.cognitive.microsoft.com/face/v1.0/detect { "url": "<path-to-image>" } @jawache

  27. @jawache

  28. Summary @jawache

  29. • Neural Networks are incredibly powerful • Conceptually, they are

    simple to understand @jawache Summary

  30. TensorFlow, MobileNet & I'm fine @jawache

  31. @jawache

  32. @jawache

  33. @jawache

  34. TensorFlow.js @jawache

  35. TensorFlow.js Train models Load pre-trained models @jawache

  36. https://github.com/tensorflow/tfjs-models @jawache MobileNet

  37. https://azure.microsoft.com/services/cognitive-services/computer-vision/ @jawache

  38. https://codepen.io/sdras/full/jawPGa/ @jawache

  39. @jawache https://twitter.com/ollee/status/930303340516216832

  40. @jawache https://twitter.com/FrontendNE/status/930120267992616960

  41. @jawache https://twitter.com/chrispiecom/status/930407801402347520

  42. Summary @jawache

  43. • TensorFlow.js doesn't have any dependancies • MobileNet is a

    simple way to analyse images • Azure Computer Vision API ❤ @jawache Summary

  44. Image2Image @jawache

  45. DEMO @jawache https://zaidalyafeai.github.io/pix2pix/cats.html

  46. @jawache Generator Discriminator ✅ ❌

  47. @jawache Generator Discriminator ✅ ❌

  48. @jawache Generator Discriminator ✅ ✅

  49. @jawache

  50. @jawache

  51. @jawache

  52. @jawache https://github.com/NVIDIA/vid2vid

  53. @jawache https://github.com/NVIDIA/vid2vid

  54. @jawache https://github.com/NVIDIA/vid2vid

  55. https://github.com/NVIDIA/vid2vid @jawache

  56. @jawache https://github.com/hanzhanggit/StackGAN

  57. Summary @jawache

  58. • 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

  59. @jawache aka.ms/mojifier

  60. @jawache themojifer.com

  61. Tero Parviainen creative.ai Music and AI in the Browser with

    TensorFlow.js and Magenta.js

  62. Thoughts @jawache

  63. Asim Hussain @jawache codecraft.tv microsoft.com