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

DevFest - Machine Learning on the Web

Avatar for Galuh Sahid Galuh Sahid
November 30, 2019
Technology
2
320

DevFest - Machine Learning on the Web

DevFest SG 2019
GitHub: https://github.com/galuhsahid/ml-on-the-web
Avatar for Galuh Sahid

Galuh Sahid

November 30, 2019
Tweet

More Decks by Galuh Sahid

See All by Galuh Sahid
CLIP Indonesian
Avatar for Galuh Sahid galuhsahid
0
200
Introduction to NLP
Avatar for Galuh Sahid galuhsahid
0
100
Implementation of AI & ML Technology in Indonesia’s Industry
Avatar for Galuh Sahid galuhsahid
0
260
BERT for Text Classification with Keras/TensorFlow 2
Avatar for Galuh Sahid galuhsahid
0
200
Introduction to Machine Learning (Nusantech Webinar)
Avatar for Galuh Sahid galuhsahid
1
540
Introduction to Machine Learning (UX Indonesia Meetup)
Avatar for Galuh Sahid galuhsahid
0
490
A Whirlwind Tour of Machine Learning with TensorFlow
Avatar for Galuh Sahid galuhsahid
0
430
First Steps Towards Your First Machine Learning Project
Avatar for Galuh Sahid galuhsahid
0
470
Call for Proposals 101
Avatar for Galuh Sahid galuhsahid
0
150

Other Decks in Technology

See All in Technology
MUITにおける開発プロセスモダナイズの取り組みと開発生産性可視化の取り組みについて / Modernize the Development Process and Visualize Development Productivity at MUIT
Avatar for 三菱UFJインフォメーションテクノロジー株式会社 muit
1
15k
AI時代の開発生産性を加速させるアーキテクチャ設計
Avatar for PLAID Tech plaidtech
PRO
3
120
B2C＆B2B＆社内向けサービスを抱える開発組織におけるサービス価値を最大化するイニシアチブ管理
Avatar for Belong inc. belongadmin
1
6.1k
ネットワーク保護はどう変わるのか？re:Inforce 2025最新アップデート解説
Avatar for Shun Tokuyama tokushun
0
190
ビズリーチが挑む メトリクスを活用した技術的負債の解消 / dev-productivity-con2025
Avatar for Visional Engineering ＆ Design visional_engineering_and_design
3
6.7k
PO初心者が考えた ”POらしさ”
Avatar for (Ha)rady nb_rady
0
190
整頓のジレンマとの戦い〜Tidy First?で振り返る事業とキャリアの歩み〜/Fighting the tidiness dilemma〜Business and Career Milestones Reflected on in Tidy First?〜
Avatar for 株式会社ビットキー / Bitkey Inc. bitkey
2
14k
CursorによるPMO業務の代替 / Automating PMO Tasks with Cursor
Avatar for Motoyoshi Kosei motoyoshi_kakaku
2
930
開発生産性を測る前にやるべきこと - 組織改善の実践 / Before Measuring Dev Productivity
Avatar for 株式会社カオナビ kaonavi
3
1.2k
Backlog ユーザー棚卸しRTA、多分これが一番早いと思います
Avatar for あれ __allllllllez__
1
140
生成AI開発案件におけるClineの業務活用事例とTips
Avatar for Shinya Masadome（東京AI祭） shinya337
0
240
高速なプロダクト開発を実現、創業期から掲げるエンタープライズアーキテクチャ
Avatar for かわうそ kawauso
2
8.3k

Featured

See All Featured
The Art of Programming - Codeland 2020
Avatar for Erika Heidi erikaheidi
54
13k
Practical Orchestrator
Avatar for Shlomi Noach shlominoach
188
11k
Navigating Team Friction
Avatar for Lara Hogan lara
187
15k
The Psychology of Web Performance [Beyond Tellerrand 2023]
Avatar for Tammy Everts tammyeverts
48
2.9k
Art, The Web, and Tiny UX
Avatar for Lynn Fisher lynnandtonic
299
21k
Build your cross-platform service in a week with App Engine
Avatar for Jose L jlugia
231
18k
The Web Performance Landscape in 2024 [PerfNow 2024]
Avatar for Tammy Everts tammyeverts
8
680
Product Roadmaps are Hard
Avatar for C. Todd Lombardo iamctodd
PRO
54
11k
For a Future-Friendly Web
Avatar for Brad Frost brad_frost
179
9.8k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
Avatar for soudai sone soudai
PRO
181
53k
Keith and Marios Guide to Fast Websites
Avatar for Keith Pitt keithpitt
411
22k
How To Stay Up To Date on Web Technology
Avatar for Chris Coyier chriscoyier
790
250k

Transcript

  1. None

  2. Machine Learning on the Web DevFest SG - November 30,

    2019

  3. Hi! I’m Galuh Twitter: @galuhsahid https://galuh.me

  4. Machine learning gives computers the ability to learn without being

    explicitly programmed. - Arthur Samuel (1959)

  5. Computer Rules Output Data

  6. Computer Data Output Rules Computer Rules Output Data

  7. Ingredients of machine learning

  8. Data: Pictures https://www.rainforest-alliance.org/sites/default/files/styles/750w_585h/public/2016-09/three-toed-sloth.jpg?itok=uWF-NdZZ https://www.thoughtco.com/thmb/DpVtY--UXVOtG68m9LhMY7be2w0=/768x0/filters:no_upscale():max_bytes(150000):strip_icc()/happy-red-panda-171399380-5b574325c9e77c005b690b41.jpg

  9. Data: Voice

  10. Data: Text

  11. Features

  12. Features

  13. Features

  14. Mathematical representation of a real life process. Model 2000*number of

    floors + … + 5000*number of rooms = house price

  15. 2000*number of floors + … + 5000*number of rooms =

    house price Model error = $5400

  16. 2000*number of floors + … + 5000*number of rooms =

    house price Model error = $5400 3000*number of floors + … + 5000*number of rooms = house price error = $4000

  17. 2000*number of floors + … + 5000*number of rooms =

    house price Model error = $5400 3000*number of floors + … + 5000*number of rooms = house price error = $4000 3000*number of floors + … + 2000*number of rooms = house price error = $2500

  18. Machine learning on the web?

  19. Machine learning on the web? “A WebGL accelerated JavaScript library

    for training and deploying ML models.”

  20. Why TensorFlow.js? Browser: !Without installation

  21. Why TensorFlow.js? Browser: !Without installation !Interactive

  22. Augmented Reality Speech Recognition Accessibility Education Conversational AI

  23. Why TensorFlow.js? Browser: !Without installation !Interactive !Data stays in the

    client

  24. Why TensorFlow.js? Browser: !Without installation !Interactive !Data stays in the

    client Server: !Nicely integrates with existing node.js stack

  25. Why TensorFlow.js? Browser: !Without installation !Interactive !Data stays in the

    client Server: !Nicely integrates with existing node.js stack

  26. How come?

  27. None

  28. Machine learning on the web? A machine learning library for

    JavaScript built on top of TensorFlow.js

  29. Machine learning on the web? A machine learning library for

    JavaScript built on top of TensorFlow.js

  30. Running pre-trained models

  31. Image classification app

  32. Input: file upload

  33. MobileNet Mobile-first computer vision model Small, low-latency, low-power

  34. MobileNet Mobile-first computer vision model Small, low-latency, low-power

  35. Image classification with MobileNet MobileNet Prediction: Bicycle (0.7845)

  36. None
  37. None
  38. None

  39. https://teachablemachine.withgoogle.com/

  40. https://teachablemachine.withgoogle.com/

  41. https://teachablemachine.withgoogle.com/

  42. None
  43. None

  44. Input: webcam

  45. None
  46. None

  47. MobileNet

  48. MobileNet DarkNet

  49. Retraining existing models

  50. New data MobileNet Prediction: ? Prediction: ?

  51. Should we train from scratch? 14 million images

  52. Transfer learning MobileNet trained on a new task Prediction: Angklung

    (0.873)

  53. Rock Paper Scissors

  54. Rock Paper Scissors: Demo

  55. None
  56. None
  57. None
  58. None
  59. None
  60. None
  61. None

  62. Transfer learning MobileNet Bicycle (0.373) Cup (0.232) Vacuum (0.121)

  63. Transfer learning MobileNet Bicycle (0.373) Cup (0.232) Vacuum (0.121) x

  64. Transfer learning MobileNet Rock (0.923) Paper (0.422) Scissors (0.231)

  65. Transfer learning Credit: MathWorks

  66. None
  67. None
  68. None
  69. None
  70. None

  71. Scroll with Your Voice

  72. Scroll with Your Voice: Demo

  73. Sound Classification: Data

  74. Sound Classification: Model

  75. Sound Classification: Model CNN Prediction: Up (0.86)

  76. None
  77. None
  78. None

  79. … and many more https://ml5js.org/reference/

  80. Building new models from scratch

  81. index.html <html> <head> <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs/dist/ tf.min.js"></script> </head> <body> <div id="output_field"></div>

    </body> … Credit: Laurence Moroney

  82. index.html … <script> async function learnLinear(){ const model = tf.sequential();

    model.add(tf.layers.dense({units: 1, inputShape: [1]})); } learnLinear(); </script> Credit: Laurence Moroney

  83. index.html … <script> async function learnLinear(){ const model = tf.sequential();

    model.add(tf.layers.dense({units: 1, inputShape: [1]})); model.compile({ loss: 'meanSquaredError', optimizer: 'sgd' }); } learnLinear(); </script> Credit: Laurence Moroney

  84. index.html … <script> async function learnLinear(){ const model = tf.sequential();

    model.add(tf.layers.dense({units: 1, inputShape: [1]})); model.compile({ loss: 'meanSquaredError', optimizer: 'sgd' }); const xs = tf.tensor2d([-1, 0, 1, 2, 3, 4], [6, 1]); const ys = tf.tensor2d([-3, -1, 1, 3, 5, 7], [6, 1]); } learnLinear(); </script> Credit: Laurence Moroney

  85. index.html … <script> async function learnLinear(){ const model = tf.sequential();

    model.add(tf.layers.dense({units: 1, inputShape: [1]})); model.compile({ loss: 'meanSquaredError', optimizer: 'sgd' }); const xs = tf.tensor2d([-1, 0, 1, 2, 3, 4], [6, 1]); const ys = tf.tensor2d([-3, -1, 1, 3, 5, 7], [6, 1]); } learnLinear(); </script> Credit: Laurence Moroney y=2x-1

  86. index.html … <script> async function learnLinear(){ const model = tf.sequential();

    model.add(tf.layers.dense({units: 1, inputShape: [1]})); model.compile({ loss: 'meanSquaredError', optimizer: 'sgd' }); const xs = tf.tensor2d([-1, 0, 1, 2, 3, 4], [6, 1]); const ys = tf.tensor2d([-3, -1, 1, 3, 5, 7], [6, 1]); await model.fit(xs, ys, { epochs: 500 }); } learnLinear(); Credit: Laurence Moroney

  87. index.html … model.compile({ loss: 'meanSquaredError', optimizer: 'sgd' }); const xs

    = tf.tensor2d([-1, 0, 1, 2, 3, 4], [6, 1]); const ys = tf.tensor2d([-3, -1, 1, 3, 5, 7], [6, 1]); document.getElementById("output_field").innerText = model.predict( tf.tensor2d([10], [1, 1]) ); } learnLinear(); </script> </html> Credit: Laurence Moroney y=2x-1 2(10)-1 = 19
  88. None

  89. What’s next? ! A Beginner’s Guide to Machine Learning in

    JavaScript by Daniel Shiffman ! Magenta.js - music & art with machine learning ! Coursera: Machine Learning by Andrew Ng ! Machine learning + hardware ! ml5.js source code ! Bias in machine learning - book reference: Weapons of Math Destruction oleh Cathy O’Neil

  90. Thank you!