Machines are Learning: Bringing Powerful Artificial Intelligence Tools to Developers

Machines are Learning: Bringing Powerful Artificial Intelligence Tools to Developers

WAJUG, Liège, November 20th, 2017

Have you always wanted to add predictive capabilities or conversational interfaces to your application, but haven’t been able to find the time or the right technology to get started?
Everybody wants to build smart apps, but only a few are Data Scientists. This session will help you understand machine learning terminology & challenges.

7c9b8b368924556d8642bdaed3ded1f5?s=128

Danilo Poccia

November 20, 2017
Tweet

Transcript

  1. Machines are Learning Bringing Powerful Artificial Intelligence to All Developers

    Danilo Poccia AWS Technical Evangelist @danilop danilop@amazon.com danilop
  2. Credit: Gerry Cranham/Fox Photos/Getty Images http://www.telegraph.co.uk/travel/destinations/europe/united-kingdom/england/london/galleries/The-history-of-the-Tube-in-pictures-150-years-of-London-Underground/1939-ticket-examin/

  3. 1939 London Underground Credit: Gerry Cranham/Fox Photos/Getty Images http://www.telegraph.co.uk/travel/destinations/europe/united-kingdom/england/london/galleries/The-history-of-the-Tube-in-pictures-150-years-of-London-Underground/1939-ticket-examin/

  4. Data Predictions

  5. Data Model Predictions

  6. Model

  7. http://www.thehudsonvalley.com/articles/60-years-ago-today-local-technology-demonstrated-artificial-intelligence-for-the-first-time 1959 Arthur Samuel

  8. Machine Learning

  9. Machine Learning Supervised Learning Inferring a model from labeled training

    data
  10. Machine Learning Supervised Learning Unsupervised Learning Inferring a model from

    labeled training data Inferring a model to describe hidden structure from unlabeled data
  11. Reinforcement Learning Perform a certain goal in a dynamic environment

    Machine Learning Supervised Learning Unsupervised Learning
  12. Driving a vehicle Playing a game against an opponent

  13. Clustering

  14. Clustering

  15. Tip: Try topic modeling with your own emails ;-) Topic

    Modeling Discovering abstract “topics” that occur in a collection of documents For example, looking for “infrequent” words that are used more often in a document
  16. Regression “How many bikes will be rented tomorrow?” Happy, Sad,

    Angry, Confused, Disgusted, Surprised, Calm, Unknown Binary Classification Multi-Class Classification “Is this email spam?” “What is the sentiment of this tweet, or of this social media comment?” 1, 0, 100K Yes / No True / False %
  17. Training the Model Minimizing the Error of using the Model

    on the Labeled Data
  18. Validation How well is this Model working on New Data?

  19. Be Careful of Overfitting

  20. Be Careful of Overfitting

  21. Be Careful of Overfitting

  22. Better Fitting

  23. Better Fitting

  24. Different Models ⇒ Different Predictions

  25. Labeled Data

  26. Labeled Data 70% 30% Training Validation

  27. Neural Networks

  28. 1943 Warren McCulloch, Walter Pitts Threshold Logic Units

  29. 1962 Frank Rosenblatt Perceptron

  30. ∑ w1 w2 w3 wn w0 = output weights (parameters)

    activation function input
  31. f(∑) w1 w2 w3 wn w0 = weights (parameters) activation

    function output input
  32. f(∑) input output

  33. 1969 Marvin Minsky, Seymour Papert Perceptrons: An Introduction to Computational

    Geometry A perceptron can only solve linearly separable functions (e.g. no XOR)
  34. f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) input

    layer hidden layer output layer input output Multiple Layers Lots of Parameters Backpropagation
  35. Microprocessor Transistor Counts 1971-2011 Intel Xeon CPU 28 cores NVIDIA

    V100 GPU 5,120 CUDA Cores 640 Tensor Cores https://en.wikipedia.org/wiki/Moore's_law
  36. LeCun, Gradient-Based Learning Applied to Document Recognition,1998 Hinton, A Fast

    Learning Algorithm for Deep Belief Nets, 2006 Bengio, Learning Deep Architectures for AI, 2009 Advances in Research 1998-2009
  37. “Stacks of differentiable non-linear functions with lots of parameters solve

    nearly any predictive modeling problem” —Jeremy Howard, fast.ai
  38. Image Processing

  39. f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) output

    How to give images in input to a Neural Network? Photo by David Iliff. License: CC-BY-SA 3.0 https://commons.wikimedia.org/wiki/File:Colosseum_in_Rome,_Italy_-_April_2007.jpg
  40. Convolution Matrix 0 0 0 0 1 0 0 0

    0 Identity Photo by David Iliff. License: CC-BY-SA 3.0 https://commons.wikimedia.org/wiki/File:Colosseum_in_Rome,_Italy_-_April_2007.jpg
  41. Convolution Matrix 1 0 -1 2 0 -2 1 0

    -1 Left Edges Photo by David Iliff. License: CC-BY-SA 3.0 https://commons.wikimedia.org/wiki/File:Colosseum_in_Rome,_Italy_-_April_2007.jpg
  42. Convolution Matrix -1 0 1 -2 0 2 -1 0

    1 Right Edges Photo by David Iliff. License: CC-BY-SA 3.0 https://commons.wikimedia.org/wiki/File:Colosseum_in_Rome,_Italy_-_April_2007.jpg
  43. Convolution Matrix 1 2 1 0 0 0 -1 -2

    -1 Top Edges Photo by David Iliff. License: CC-BY-SA 3.0 https://commons.wikimedia.org/wiki/File:Colosseum_in_Rome,_Italy_-_April_2007.jpg
  44. Convolution Matrix -1 -2 -1 0 0 0 1 2

    1 Bottom Edges Photo by David Iliff. License: CC-BY-SA 3.0 https://commons.wikimedia.org/wiki/File:Colosseum_in_Rome,_Italy_-_April_2007.jpg
  45. Convolution Matrix 0.6 -0.6 1.2 -1.4 1.2 -1.6 0.8 -1.4

    1.6 Random Values Photo by David Iliff. License: CC-BY-SA 3.0 https://commons.wikimedia.org/wiki/File:Colosseum_in_Rome,_Italy_-_April_2007.jpg
  46. Convolutional Neural Networks (CNNs) https://en.wikipedia.org/wiki/Convolutional_neural_network

  47. ImageNet Classification Error Over Time 0 5 10 15 20

    25 30 2010 2011 2012 2013 2014 2015 2016 2017 Classification Error CNNs
  48. 2012 ImageNet Classification with Deep Convolutional Neural Networks

  49. SuperVision: 8 layers, 60M parameters 0

  50. 2013 Visualizing and Understanding Convolutional Networks

  51. None
  52. None
  53. How Do Neural Networks Learn? ? More generic and can

    be reused as feature extractor for other visual tasks Specific to task Cat Dog 0
  54. The Challenge For Machine Learning: Scale Aggressive migration New data

    created on AWS PBs of existing data Data
  55. The Challenge For Machine Learning: Scale Tons of GPUs Elastic

    capacity Pre-built images Aggressive migration New data created on AWS PBs of existing data Data Training
  56. The Challenge For Machine Learning: Scale Tons of GPUs and

    CPUs Serverless At the edge, on IoT Devices Tons of GPUs Elastic capacity Pre-built images Aggressive migration New data created on AWS PBs of existing data Data Training Prediction
  57. Natural Language Processing Experiment: Topic Modeling EC2 Spot Instances 1.1

    Million vCPUs
  58. Fulfilment & logistics Search & discovery Existing products New products

    Thousands Of Amazon Engineers Focused On Machine Learning
  59. None
  60. None
  61. Machine Learning On AWS Today

  62. Artificial Intelligence In The Hands Of Every Developer S E

    R V I C E S P L A T F O R M S E N G I N E S I N F R A S T R U C T U R E GPU CPU IoT Mobile Apache MXNet Caffe 2 Theano PyTorch CNTK TensorFlow
  63. Early Detection Of Diabetic Complications

  64. FDA-approved Medical Imaging

  65. Sports Analytics

  66. Autonomous Driving Systems

  67. Real Time, Per Pixel Object Segmentation

  68. Centimeter-accurate Positioning

  69. Computation Knowledge Engine

  70. None
  71. S E R V I C E S P L

    A T F O R M S E N G I N E S I N F R A S T R U C T U R E Amazon ML Spark & EMR Kinesis Batch ECS GPU CPU IoT Mobile Apache MXNet Caffe 2 Theano PyTorch CNTK TensorFlow Artificial Intelligence In The Hands Of Every Developer
  72. S E R V I C E S P L

    A T F O R M S Vision Amazon Rekognition E N G I N E S I N F R A S T R U C T U R E Amazon ML Spark & EMR Kinesis Batch ECS GPU CPU IoT Mobile Apache MXNet Caffe 2 Theano PyTorch CNTK TensorFlow Artificial Intelligence In The Hands Of Every Developer
  73. Mona Lisa (Leonardo da Vinci)

  74. None
  75. None
  76. None
  77. Mona Lisa (Prado's version)

  78. Portrait of Maddalena Doni (Raphael)

  79. Bynder allows you to easily create, find and use content

    for branding automation and marketing solutions. With our new AI capabilities, Bynder’s software… now allows users to save hours of admin labor when uploading and organizing their files, adding exponentially more value. Chris Hall CEO, Bynder ” “ With Rekognition, Bynder revolutionizes marketing admin tasks with AI capabilities
  80. S E R V I C E S P L

    A T F O R M S Speech Amazon Polly Vision Amazon Rekognition E N G I N E S I N F R A S T R U C T U R E Amazon ML Spark & EMR Kinesis Batch ECS GPU CPU IoT Mobile Apache MXNet Caffe 2 Theano PyTorch CNTK TensorFlow Artificial Intelligence In The Hands Of Every Developer
  81. Generate Lifelike Speech With Amazon Polly 25 languages “The temperature

    in Milanis 16 degrees Celsius” “The temperature in Milan is 16˚C” Amazon Polly 52 voices
  82. aws polly synthesize-speech --text "It was nice to live such

    a wonderful live show." --output-format mp3 --voice-id Joanna --text-type text output.mp3
  83. Duolingo voices its language learning service Using Polly Duolingo is

    a free language learning service where users help translate the web and rate translations. With Amazon Polly our users benefit from the most lifelike Text-to-Speech voices available on the market. Severin Hacker CTO, Duolingo ” “ • Spoken language crucial for language learning • Accurate pronunciation matters • Faster iteration thanks to TTS • As good as natural human speech
  84. ” “ Royal National Institute of Blind People creates and

    distributes accessible information in the form of synthesized content Amazon Polly delivers incredibly lifelike voices which captivate and engage our readers. John Worsfold Solutions Implementation Manager, RNIB • RNIB delivers largest library of audiobooks in the UK for nearly 2 million people with sight loss • Naturalness of generated speech is critical to captivate and engage readers • No restrictions on speech redistributions enables RNIB to create and distribute accessible information in a form of synthesized content RNIB provides the largest library in the UK for people with sight loss
  85. S E R V I C E S P L

    A T F O R M S Chat Amazon Lex Speech Amazon Polly Vision Amazon Rekognition E N G I N E S I N F R A S T R U C T U R E Amazon ML Spark & EMR Kinesis Batch ECS GPU CPU IoT Mobile Apache MXNet Caffe 2 Theano PyTorch CNTK TensorFlow Artificial Intelligence In The Hands Of Every Developer
  86. Amazon Lex Speech recognition and natural language understanding Automatic speech

    recognition Natural language understanding “What’s the weather forecast?” Weather forecast Amazon Lex
  87. Amazon Lex Speech recognition and natural language understanding “It will

    be sunny and 16C” Automatic speech recognition Natural language understanding “What’s the weather forecast?” Weather forecast Amazon Lex
  88. “It will be sunny and 16 degrees Celsius” Amazon Polly

    Amazon Lex “It will be sunny and 16C” Automatic speech recognition Natural language understanding “What’s the weather forecast?” Weather forecast Speech recognition and natural language understanding Amazon Lex
  89. ” “ Finding missing persons: ~100,000 active missing persons cases

    in the U.S. at any given time ~60% are adults, ~40% are children • Motorola Solutions applies Amazon Rekognition, Amazon Polly and Amazon Lex • Image analytics and facial recognition can continually monitor for missing persons • Tools that understand natural language can enable officers to keep eyes up and hands free Motorola Solutions is using AI to help finding missing persons Motorola Solutions keeps utility workers connected and visible to each other with real-time voice and data communication across the smart grid.
  90. S E R V I C E S P L

    A T F O R M S Chat Amazon Lex Speech Amazon Polly Vision Amazon Rekognition E N G I N E S I N F R A S T R U C T U R E Amazon ML Spark & EMR Kinesis Batch ECS GPU CPU IoT Mobile Apache MXNet Caffe 2 Theano PyTorch CNTK TensorFlow
  91. There’s Never Been A Better Time To Build Smart Apps

  92. https://github.com/danilop/security-camera

  93. Machines are Learning Bringing Powerful Artificial Intelligence to All Developers

    Danilo Poccia AWS Technical Evangelist @danilop danilop@amazon.com danilop