the magic of unsupervised learning agustinus nalwan
play

THE MAGIC OF UNSUPERVISED LEARNING Agustinus Nalwan Head of AI - PowerPoint PPT Presentation

Aug 22, 2022 •279 likes •1.11k views

THE MAGIC OF UNSUPERVISED LEARNING Agustinus Nalwan Head of AI Carsales.com.au A LITTLE BIT ABOUT MYSELF AI 4 Years SAVING OUR FOREST BUSHFIRE DETECTION BACK TO THE MAIN TOPIC THE MAGIC OF UNSUPERVISED LEARNING SUPERVISED LEARNING

  1. THE MAGIC OF UNSUPERVISED LEARNING Agustinus Nalwan Head of AI Carsales.com.au

  2. A LITTLE BIT ABOUT MYSELF AI 4 Years

  3. SAVING OUR FOREST BUSHFIRE DETECTION

  5. BACK TO THE MAIN TOPIC

  6. THE MAGIC OF UNSUPERVISED LEARNING

  7. SUPERVISED LEARNING

  8. SUPERVISED LEARNING IMAGE RECOGNITION

  11. CAR RECOGNITION

  13. Ford Kuga Titanium

  14. SUPERVISED LEARNING I am awesome

  15. HOW DO YOU TRAIN THE AI?

  16. TRAINING BMW X5 Ford Ecosport Hyundai i30

  17. LOTS OF THEM

  18. SERIOUSLY LOTS OF THEM

  19. 10,000,000 CARS

  20. 10,000,000 CARS LABELLED!

  23. FROM MULTIPLE ANGLES

  24. PROBLEMS • Huge effort • Not practical

  25. MOST WORLD DATAS ARE UNLABELED • Facebook photos • Youtube videos • Twitter feeds

  26. UNSUPERVISED LEARNING

  27. UNSUPERVISED DEEP LEARNING GENERATING FACES

  28. IMAGE GENERATION • Variational Auto Encoder (VAE) • Generative Adversarial Network (GAN)

  29. VAE • Understand the subject (face) • Generate new subject

  30. HOW DOES IT WORK?

  31. AUTOENCODER 20x20 40x40 80x80 80x80 40x40 20x20 50x1 Latent Vector Decoder Encoder

  32. MSE, FPL - Error Images Minimize

  33. LATENT VECTORS Reconstructed Original Image Image 8.5 5.2 8.7 -3.2 1.5 -2.4 4.3 4.5 5.4 4.2 -2.0 0.9 4.3 -3.5 1.4

  34. LATENT VECTORS Reconstructed Original Image Image 8.5 5.2 8.7 -3.2 1.5 -2.4 4.3 4.5 5.4 4.2 -2.0 0.9 4.3 -3.5 1.4 Hair-length

  35. LATENT VECTORS Reconstructed Original Image Image 8.5 5.2 8.7 -3.2 1.5 -2.4 4.3 4.5 5.4 4.2 -2.0 0.9 4.3 -3.5 1.4 Hair-length Skin-color

  36. LATENT VECTORS Reconstructed Original Image Image 8.5 5.2 8.7 -3.2 1.5 -2.4 4.3 4.5 5.4 4.2 -2.0 0.9 4.3 -3.5 1.4 Hair-length Skin-color Eye-size Gender Age

  37. HOW COULD IT BE POSSIBLE? SMALL LATENT DIMENSION REMEMBER THE SIGNIFICANT DIFFERENCES

  38. PACKING A TRAVEL BAG

  39. BIG LUGGAGE

  40. SMALL BAG Latent Vector Important Features Learned

  41. MEMORY GAMES Info 1 Info 2 Info 3 Info 4 Info 1 Info 2 Info 3 Info 4 Gender Hair Color Skin Color Age

  42. HOW DO WE USE IT TO GENERATE NEW FACE?

  43. AUTOENCODER 20x20 40x40 80x80 80x80 40x40 20x20 50x1 Latent Vector Decoder Encoder

  44. AUTOENCODER 50x1 20.1, 10.5, -5.2, 6.2, … Latent Vector Decoder

  45. AUTOENCODER 50x1 20.1, 10.5, -5.2, 6.2, … Latent Vector Decoder

  46. LATENT SPACE DISTRIBUTION Land of no face

  47. LATENT SPACE

  48. MORPHING

  49. FACE ARITHMETIC

  50. LATENT VECTORS Reconstructed Original Image Image 8.5 5.2 8.7 -3.2 1.5 -2.4 4.3 4.5 5.4 4.2 -2.0 0.9 4.3 -3.5 1.4 Hair-length Skin-color Eye-size Gender Age

  51. LATENT VECTORS Reconstructed Original Image Image 8.5 5.2 8.7 -3.2 1.5 -2.4 4.3 4.5 5.4 4.2 -2.0 0.9 4.3 -3.5 1.4 Hair-length

  52. LATENT VECTORS Reconstructed Original Image Image 8.5 5.2 8.7 -3.2 1.5 -2.4 4.3 4.5 5.4 4.2 -2.0 0.9 4.3 -3.5 1.4 0.7 0.1 0.2 Hair-length

  53. 20.1, 10.5, -5.2 5.0, 6.3, -5.6 Bang vector 15.1, 4.2, 0.4

  54. BANG PREVIEW Bang vector 1.0, 5.3, 3.2 15.1, 4.2, 0.4 16.1, 9.5, 3.6

  55. ADDING GLASSES

  56. REMOVING GLASSES

  57. ADDING YOUTH

  58. GAN 
 GENERATIVE ADVERSARIAL NETWORK

  59. Real Face Discriminator Prediction Images Network Real or Fake Punished on Discriminator Network’s Generated failure Face Image Punished on Discriminator Network’s Generative Random Vector success Network

  60. MORPHING USING GAN

  62. OTHER APPLICATION OF GENERATIVE NETWORK

  63. SUPER RESOLUTION

  64. SUPER RESOLUTION

  65. SUPER RESOLUTION

  66. SUPER RESOLUTION

  67. SUPER RESOLUTION

  68. SUPER RESOLUTION

  69. SUPER RESOLUTION 256x512 64x128 4x

  70. SUPER RESOLUTION

  71. UNSUPERVISED LEARNING WHY IS IT IMPORTANT ?

  72. AGI

  73. WHAT’S NEEDED FOR AN AGI

  74. SELF LEARNING Supervised Unsupervised

  75. KNOWLEDGE EXTRACTION

  76. REASONING Reasoning Knowledge Extraction Information

  77. WITHOUT REASONING

  78. WITHOUT REASONING

  79. TAKE AWAY NOTHING

  80. DANGER !!!

  81. THANK YOU

  82. QUESTION?

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Agustinus Nalwan Head of AI Carsales.com.au Carsales Car Buying & Selling Private

Agustinus Nalwan Head of AI Carsales.com.au Carsales Car Buying & Selling Private

MYSTIQUE THE FIGHT AGAINST REGO PLATE CLONER Agustinus Nalwan Head of AI Carsales.com.au Carsales Car Buying & Selling Private and Dealer +230k cars 5000 new cars /day Bikes, boats, trucks, A LITTLE BIT ABOUT

1.36k views • 82 slides
UNSUPERVISED LEARNING, CLUSTERING UNSUPERVISED LEARNING UNSUPERVISED LEARNING Supervised

UNSUPERVISED LEARNING, CLUSTERING UNSUPERVISED LEARNING UNSUPERVISED LEARNING Supervised

UNSUPERVISED LEARNING, CLUSTERING UNSUPERVISED LEARNING UNSUPERVISED LEARNING Supervised learning: X - y pairs, f(x) function approximation Unsupervised learning: only X, no y Exploring the space of X measurements,

440 views • 14 slides
Introduction to PCA Unsupervised Learning in R Unsupervised learning Two methods of

Introduction to PCA Unsupervised Learning in R Unsupervised learning Two methods of

UNSUPERVISED LEARNING IN R Introduction to PCA Unsupervised Learning in R Unsupervised learning Two methods of clustering finding groups of homogeneous items Next up, dimensionality reduction Find structure in features

904 views • 29 slides
Unsupervised Learning and Clustering l In unsupervised learning you are given a data set with no

Unsupervised Learning and Clustering l In unsupervised learning you are given a data set with no

Unsupervised Learning and Clustering l In unsupervised learning you are given a data set with no output classifications (labels) l Clustering is an important type of unsupervised learning PCA was another type of unsupervised learning l The

858 views • 38 slides
Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on

Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on

Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on supervised learning methods such as regression and classification. In that setting we observe both a set of features X 1 , X 2 , . . . , X p for each

934 views • 50 slides
Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on

Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on

Unsupervised Learning Unsupervised vs Supervised Learning: Most of this course focuses on supervised learning methods such as regression and classification. In that setting we observe both a set of features X 1 , X 2 , . . . , X p for each

721 views • 60 slides
Unsupervised Learning Andrea Passerini passerini@disi.unitn.it Machine Learning Unsupervised

Unsupervised Learning Andrea Passerini passerini@disi.unitn.it Machine Learning Unsupervised

Unsupervised Learning Andrea Passerini passerini@disi.unitn.it Machine Learning Unsupervised Learning Unsupervised Learning Setting Supervised learning requires the availability of labelled examples Labelling examples can be an extremely

752 views • 27 slides
12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from Wanli Ouyang, Zsolt Kira, Lawrence Neal, Raymond Yeh, Junting Lou and Teck-Yian Lim Unsupervised Learning in General Unsupervised learning is

1.48k views • 115 slides
Machine Learning for NLP Unsupervised Learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Unsupervised Learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Unsupervised Learning Aurlie Herbelot 2019 Centre for Mind/Brain Sciences University of Trento 1 Unsupervised learning In unsupervised learning, we learn without training data. The idea is to find a

998 views • 67 slides
Unsupervised Learning Introduction Nakul Verma Unsupervised Learning What can we learn from

Unsupervised Learning Introduction Nakul Verma Unsupervised Learning What can we learn from

Unsupervised Learning Introduction Nakul Verma Unsupervised Learning What can we learn from data when label information is not available? Supervised learning framework Supervised learning Data: Assumption: there is a (relatively simple)

442 views • 16 slides
Practical Unsupervised Learning INFO/CS 4300, Spring 2016 Jack Hessel Unsupervised Learning is

Practical Unsupervised Learning INFO/CS 4300, Spring 2016 Jack Hessel Unsupervised Learning is

Practical Unsupervised Learning INFO/CS 4300, Spring 2016 Jack Hessel Unsupervised Learning is Cool! But how can we use this in our projects? 1. 2. But first, lets look at our dataset... Data Dimensionality! Probability of Lung Cancer

999 views • 55 slides
Automatic Learning of a Morphological Model Theory and Unsupervised Approaches Unsupervised

Automatic Learning of a Morphological Model Theory and Unsupervised Approaches Unsupervised

Automatic Learning of a Morphological Model Theory and Unsupervised Approaches Unsupervised Learning - ToC Foundations Problem description General architecture Papers: Goldsmith 2001 and 2006 Goldsmith and Hu 2004

1.23k views • 43 slides
Unsupervised learning introduction October 7, 2019 Unsupervised learning introduction

Unsupervised learning introduction October 7, 2019 Unsupervised learning introduction

Unsupervised learning introduction October 7, 2019 Unsupervised learning introduction October 7, 2019 1 / 39 Intro General statement of the problem One has a set of N observations ( x 1 , x 2 , ..., x N ) of a random p -vector X having

495 views • 32 slides
Unsupervised learning General introduction to unsupervised learning PCA Special directions

Unsupervised learning General introduction to unsupervised learning PCA Special directions

Unsupervised learning General introduction to unsupervised learning PCA Special directions These are special directions we will try to find. Best direction u : |u| 2 = 1 2 1. Minimize : d i X i T u is the projection length x i u d i T

1.01k views • 29 slides
Lecture 13: From Unsupervised to Reinforcement Learning (Chapters 8-10) R. Rao, 528: Lecture 13

Lecture 13: From Unsupervised to Reinforcement Learning (Chapters 8-10) R. Rao, 528: Lecture 13

CSE/NB 528 Lecture 13: From Unsupervised to Reinforcement Learning (Chapters 8-10) R. Rao, 528: Lecture 13 1 Todays Agenda: All about Learning F Unsupervised Learning Sparse Coding Predictive Coding F Supervised learning Perceptrons and

479 views • 24 slides
Unsupervised Deep Learning Tutorial - Part 2 Alex Graves MarcAurelio Ranzato

Unsupervised Deep Learning Tutorial - Part 2 Alex Graves MarcAurelio Ranzato

Unsupervised Deep Learning Tutorial - Part 2 Alex Graves MarcAurelio Ranzato gravesa@google.com ranzato@fb.com NeurIPS, 3 December 2018 Overview Practical Recipes of Unsupervised Learning Learning representations Learning to

1.16k views • 103 slides
Computer Graphics (CS 543) Lecture 3 (Part 1): Building 3D Models Prof Emmanuel Agu Computer

Computer Graphics (CS 543) Lecture 3 (Part 1): Building 3D Models Prof Emmanuel Agu Computer

Computer Graphics (CS 543) Lecture 3 (Part 1): Building 3D Models Prof Emmanuel Agu Computer Science Dept. Worcester Polytechnic Institute (WPI) 3D Applications 2D points: (x,y) coordinates 3D points: have (x,y,z) coordinates Setting up 3D

671 views • 34 slides
Wage Discrimination when Identity is Subjective: Evidence from Changes in Employer-Reported Race

Wage Discrimination when Identity is Subjective: Evidence from Changes in Employer-Reported Race

Wage Discrimination when Identity is Subjective: Evidence from Changes in Employer-Reported Race Christopher Cornwell Jason Rivera and Ian M. Schmutte Department of Economics University of Georgia Applied Microeconomics Workshop The Ohio

688 views • 51 slides
Efficient Rendering of Human Skin CS6630 Sunling Yang Tim Langlois Cornell University April 5,

Efficient Rendering of Human Skin CS6630 Sunling Yang Tim Langlois Cornell University April 5,

Efficient Rendering of Human Skin CS6630 Sunling Yang Tim Langlois Cornell University April 5, 2012 Outline Theory Sum of Gaussians Approximation Hardware Texture Space Diffusion Translucent Shadow Maps (TSMs) Assumptions/Approximations

558 views • 27 slides
TALKING RACE WITH YOUNG CHILDREN Dr. Erica Frankenberg Dr. Allison Henward Educators from

TALKING RACE WITH YOUNG CHILDREN Dr. Erica Frankenberg Dr. Allison Henward Educators from

TALKING RACE WITH YOUNG CHILDREN Dr. Erica Frankenberg Dr. Allison Henward Educators from Bennett Family Center and Hort Woods Child Care More than two-thirds of millenials agreed: Society would be better if it were truly colorblind and

336 views • 15 slides
Eigenfaces John Schavemaker, Wessel Kraaij, Pieter Eendebak, Mark van Staalduinen John

Eigenfaces John Schavemaker, Wessel Kraaij, Pieter Eendebak, Mark van Staalduinen John

Exhaustive SURF, small bag-of-words and Eigenfaces John Schavemaker, Wessel Kraaij, Pieter Eendebak, Mark van Staalduinen John Schavemaker TNO instance search submission TNO Netherlands research organization for Applied Scientific Research

569 views • 38 slides
Recognition Part I CSE 576 What we have seen so far: Vision as Measurement Device Real-time

Recognition Part I CSE 576 What we have seen so far: Vision as Measurement Device Real-time

Recognition Part I CSE 576 What we have seen so far: Vision as Measurement Device Real-time stereo on Mars Physics-based Vision Virtualized Reality Structure from Motion Slide Credit: Alyosha Efros Visual Recognition What does it mean

1.13k views • 110 slides
Use and Misuse of Race Information in Genomic Research Tesfaye B. Mersha, PhD Assistant

Use and Misuse of Race Information in Genomic Research Tesfaye B. Mersha, PhD Assistant

Use and Misuse of Race Information in Genomic Research Tesfaye B. Mersha, PhD Assistant Professor Division of Asthma Research Cincinnati Childrens Hospital Medical Center University of Cincinnati Why race matters? Every indicator of

928 views • 26 slides
Endogenous Segregation Dynamics and Housing Market Interactions: An ABM approach Benjamin

Endogenous Segregation Dynamics and Housing Market Interactions: An ABM approach Benjamin

Endogenous Segregation Dynamics and Housing Market Interactions: An ABM approach Benjamin Bonakdar Ruhr-University Bochum Institute for Macroeconomics benjamin.bonakdar@rub.de June 8th, 2017 Benjamin Bonakdar (RUB) Endogenous Segregation

398 views • 15 slides

More recommend