Machines are Learning: Bringing Powerful Artificial Intelligence to All Developers

Codemotion, Milan, November 10th, 2017

Have you always wanted to add predictive capabilities, image or voice recognition 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, what deep learning is and the possible use cases, how to build a machine learning model that works, and how to use developer-ready APIs for high-quality, high-accuracy AI capabilities that are scalable and cost-effective.

Transcript

1. Machines are Learning Danilo Poccia, AWS Technical Evangelist CODEMOTION MILAN - SPECIAL EDITION 10 – 11 NOVEMBER 2017
2. Machines are Learning Bringing Powerful Artificial Intelligence to All Developers Danilo Poccia AWS Technical Evangelist @danilop danilop@amazon.com danilop
3. 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. 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/
5. Data Predictions
6. Data Model Predictions
7. Model
8. http://www.thehudsonvalley.com/articles/60-years-ago-today-local-technology-demonstrated-artificial-intelligence-for-the-first-time 1959 Arthur Samuel
9. Machine Learning
10. Machine Learning Supervised Learning Inferring a model from labeled training data
11. Machine Learning Supervised Learning Unsupervised Learning Inferring a model from labeled training data Inferring a model to describe hidden structure from unlabeled data
12. Reinforcement Learning Perform a certain goal in a dynamic environment Machine Learning Supervised Learning Unsupervised Learning
13. Driving a vehicle Playing a game against an opponent
14. Clustering
15. Clustering
16. 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
17. 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 %
18. Training the Model Minimizing the Error of using the Model on the Labeled Data
19. Validation How well is this Model working on New Data?
20. Be Careful of Overfitting
21. Be Careful of Overfitting
22. Be Careful of Overfitting
23. Better Fitting
24. Better Fitting
25. Different Models ⇒ Different Predictions
26. Labeled Data
27. Labeled Data 70% 30% Training Validation
28. Neural Networks
29. 1943 Warren McCulloch, Walter Pitts Threshold Logic Units
30. 1962 Frank Rosenblatt Perceptron
31. ∑ w1 w2 w3 wn w0 = output weights (parameters) activation function input
32. f(∑) w1 w2 w3 wn w0 = weights (parameters) activation function output input
33. f(∑) input output
34. 1969 Marvin Minsky, Seymour Papert Perceptrons: An Introduction to Computational Geometry A perceptron can only solve linearly separable functions (e.g. no XOR)
35. f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) f(∑) input layer hidden layer output layer input output Multiple Layers Lots of Parameters Backpropagation
36. 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
37. 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
38. “Stacks of differentiable non-linear functions with lots of parameters solve nearly any predictive modeling problem” —Jeremy Howard, fast.ai
39. Image Processing
40. 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
41. 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
42. 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
43. 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
44. 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
45. 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
46. 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
47. Convolutional Neural Networks (CNNs) https://en.wikipedia.org/wiki/Convolutional_neural_network
48. ImageNet Classification Error Over Time 0 5 10 15 20 25 30 2010 2011 2012 2013 2014 2015 2016 2017 Classification Error CNNs
49. 2012 ImageNet Classification with Deep Convolutional Neural Networks
50. SuperVision: 8 layers, 60M parameters 0
51. 2013 Visualizing and Understanding Convolutional Networks
54. How Do Neural Networks Learn? ? More generic and can be reused as feature extractor for other visual tasks Specific to task Cat Dog 0
55. The Challenge For Machine Learning: Scale Aggressive migration New data created on AWS PBs of existing data Data
56. 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
57. 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
58. Natural Language Processing Experiment: Topic Modeling EC2 Spot Instances 1.1 Million vCPUs
59. Fulfilment & logistics Search & discovery Existing products New products Thousands Of Amazon Engineers Focused On Machine Learning
62. Machine Learning On AWS Today
63. 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
64. Early Detection Of Diabetic Complications
65. FDA-approved Medical Imaging
66. Sports Analytics
67. Autonomous Driving Systems
68. Real Time, Per Pixel Object Segmentation
69. Centimeter-accurate Positioning
70. Computation Knowledge Engine
72. 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
73. 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
74. Mona Lisa (Leonardo da Vinci)
78. Mona Lisa (Prado's version)
79. Portrait of Maddalena Doni (Raphael)
80. 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
81. 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
82. Generate Lifelike Speech With Amazon Polly 24 languages “The temperature in Milanis 16 degrees Celsius” “The temperature in Milan is 16˚C” Amazon Polly 50 voices
83. 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
84. “Nel mezzo del cammin di nostra vita mi ritrovai per una selva oscura ché la diritta via era smarrita.” https://commons.wikimedia.org/wiki/File:Portrait_de_Dante.jpg
85. 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
86. ” “ 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
87. 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
88. Amazon Lex Speech recognition and natural language understanding Automatic speech recognition Natural language understanding “What’s the weather forecast?” Weather forecast Amazon Lex
89. 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
90. “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
91. ” “ 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.
92. 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
93. There’s Never Been A Better Time To Build Smart Apps
94. https://github.com/danilop/security-camera
95. Machines are Learning Bringing Powerful Artificial Intelligence to All Developers Danilo Poccia AWS Technical Evangelist @danilop danilop@amazon.com danilop