Machine Learning for Developers

Devoxx Belgium, Antwerp, November 10th, 2016

Have you always wanted to add predictive capabilities 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. We had the same issue inside Amazon, so we created a Machine Learning engine that Developers can easily use. The same approach is now available in the AWS cloud. And we introduced Amazon Alexa to build engaging voice experiences for your services and devices: if you are a device maker, and your connected product has a microphone and a speaker, the Alexa Voice Service (AVS) enables you to add voice-powered experiences to your connected devices. And you can also use the Alexa Skills Kit (ASK) to teach new skills to Alexa!

Transcript

1. Machine Learning for Developers Danilo Poccia Technical Evangelist, AWS @danilop Sébastien Stormacq Solution Architect, Alexa @sebsto
2. What to Expect from this Session Understand Machine Learning Terminology & Challenges Implement a Machine Learning Model Add Predictive Capabilities to your App Provide Your Customer with Voice UX
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. 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/ 1939 London Underground
5. Batch Report
6. Batch Report Real-time Alerts
7. Batch Report Real-time Alerts Prediction Forecast
8. Predictions
9. Data Predictions
10. Model Data Predictions
11. Model
12. Machine Learning
13. Supervised Learning Machine Learning Unsupervised Learning The task of inferring a model from labeled training data The task of inferring a model to describe hidden structure from unlabeled data
14. Reinforcement Learning Perform a certain goal in a dynamic environment, without an explicit “teacher”
15. Driving a vehicle Playing a game
 against an opponent R einforcem ent Learning
16. Clustering U nsupervised
 Learning
17. Clustering U nsupervised
 Learning
18. Clustering U nsupervised
 Learning
19. Regression Binary Classification Multi-class Classification Supervised
 Learning
20. Validation Supervised
 Learning
21. Training from Labeled Data Supervised
 Learning Training Validation 70% 30%
22. Training the Model Minimizing the Error Function Supervised
 Learning
23. Be Careful of Overfitting Supervised
 Learning
24. Be Careful of Overfitting Supervised
 Learning
25. Be Careful of Overfitting Supervised
 Learning
26. Better Model, Different Predictions Supervised
 Learning
27. Supervised
 Learning Better Model, Different Predictions
28. Regularization Adding a “cost” for using
 large parameters in the model L1, L2 Supervised
 Learning
29. ? Data Model
30. Amazon EMR with Spark (MLib) Data Model
31. Data Scientists “Scalability”
32. Amazon
 Machine Learning
 (Amazon ML) Data Model
33. Amazon
 Machine Learning
 (Amazon ML) Data Model Batch Predictions
34. Amazon
 Machine Learning
 (Amazon ML) Data Model Batch Predictions Real-time Predictions
35. Binary Classification Multiclass Classification Regression Logistic Regression
 (Logistic Loss Function + SGD) Multinomial Logistic Regression
 (Multinomial Logistic Loss + SGD) Linear Regression
 (Squared Loss Function + SGD) The optimization technique used in Amazon ML is
 online Stochastic Gradient Descent (SGD)
36. <demo> ... </demo>
37. <demo> Bike Sharing </demo>
40. All Users
41. All Users Casual Users Registered Users
42. <demo> ... </demo>
43. What about Deep Learning?
44. Neural Networks Perceptron Layers
45. Perceptron https://upload.wikimedia.org/wikipedia/commons/8/8c/Perceptron_moj.png https://upload.wikimedia.org/wikipedia/commons/thumb/f/f1/Logistic-sigmoid-vs-scaled-probit.svg/240px-Logistic-sigmoid-vs-scaled-probit.svg.png
46. Neural Network Architectures http://www.asimovinstitute.org/neural-network-zoo/
47. Deep Learning AMI 5 Deep Learning Frameworks MXNet, Caffe, Tensorflow, Theano, and Torch Pre-installed components to speed productivity, such as Nvidia drivers, cuDNN, Anaconda, Python 2 & 3 AWS Integration R eady to use on A m azon EC 2
48. Amazon EC2 P2 Instances Up to: • 16 NVIDIA K80 GPUs • 64 vCPUs 732 GiB of host memory • combined 192 GB of GPU memory • 40 thousand parallel processing cores • 70 teraflops (single precision) • over 23 teraflops (double precision). • GPUDirect™ for up to 16 GPUs G PU Instances
49. What about interacting with devices in a more intuitive way, using voice?
51. <demo> ... </demo>
52. Create Great Content: ASK is how you connect
 to your consumer THE ALEXA ECOSYSTEM Supported by two powerful frameworks A L E X A 
 V O I C E 
 S E R V I C E Unparalleled Distribution: AVS allows your content
 to be everywhere Lives In The Cloud Automated Speech Recognition (ASR) Natural Language Understanding (NLU) Always Learning A L E X A 
 S K I L L S 
 K I T
53. UNDER THE HOOD OF ASK A closer look at how the Alexa Skills Kit process a request and returns an appropriate response You Pass Back a Textual or Audio Response You Pass Back a Graphical Response Alexa Converts Text-to-Speech (TTS) & Renders Graphical Component Respond to Intent through Text & Visual Alexa sends Customer Intent to Your Service User Makes a Request Alexa Identifies Skill & Recognizes Intent Through ASR & NLU Your Service processes Request Audio Stream is sent up to Alexa
54. ALEXA SKILL KIT High Level Overview Your Code
55. ALEXA SKILL KIT High Level Overview Amazon EC2
56. ALEXA SKILL KIT High Level Overview Availability Zone 1 Web tier App tier RDS (Master) Availability Zone 2 RDS (Standby)
57. ALEXA SKILL KIT High Level Overview Elastic Beanstalk environment Auto Scaling group Elastic Beanstalk container Auto Scaling group Elastic Beanstalk container Prod 1 Prod 2 Route 53
58. ALEXA SKILL KIT High Level Overview AWS Lambda
59. ALEXA SKILL KIT Voice Model Intents Utterances Slots
60. ALEXA SKILL KIT Voice Model Intents Utterances Slots
61. ALEXA SKILL KIT Voice Model Intents Utterances Slots
62. ALEXA SKILL KIT Voice Model Intents Utterances Slots
63. ALEXA SKILL KIT Typescript Code
64. ALEXA SKILL KIT Alexa App
65. <demo> ... </demo>
66. Your Skill (Lambda function) Amazon Machine Learning get real-time predictions invoke Weather Forecast Historical Data get forecast build & train model B ike Sharing D em o A rchitecture
67. Build Apps With Services, Not Servers
68. aws.amazon.com/free developers.amazon.com
69. Thank you! @danilop @sebsto