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

VivaTech 2019: Deep Learning Demystified

VivaTech 2019: Deep Learning Demystified

Introduction to deep learning for image classification using Amazon Web Services

Julio Faerman

May 16, 2019
Tweet

More Decks by Julio Faerman

Other Decks in Technology

Transcript

  1. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Julio Faerman, Technical Evangelist @faermanj Deep Learning, Demystified A (mostly) effortless introduction Gabe Hollombe, Technical Evangelist @gabehollombe
  2. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. What we’ll cover 1. Kick off a demo (put the cookies in the oven) 2. What’s Deep Learning? What’s a Neural Network? 3. Look at some code 4. Finish the demo (enjoy our cookies) 5. How to do this yourself 6. Where to learn more
  3. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. What is Deep Learning?
  4. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Machine Learning Using neural networks with multiple layers, which allows computers to learn from complex data without needing to explicitly define the features of the data. Neural Networks Deep Learning Computation inspired by how our brains work. Proven to be capable of performing any computation, given enough memory. Computers figuring out how to do things without being explicitly programmed.
  5. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Deep Learning A technique to help computers learn how to do things that are easy for humans but hard to explicitly program. Self-driving Cars Sentiment Analysis Object Detection Facial Recognition
  6. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark You don’t need a PHD. You don’t need a ton of data. You can start using deep learning for your own projects today. Without a dedicated data science team of experts.
  7. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. We can build and deploy a custom image classifier. Right now.
  8. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. First, let’s collect some images of things we want to classify…
  9. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. { "Labels": [ { "Name": "Skateboard", "Confidence": 99.25341796875 }, { "Name": "Sport", "Confidence": 99.25341796875 }, { "Name": "Sports", "Confidence": 99.25341796875 }, { "Name": "Human", "Confidence": 99.24723052978516 },
  10. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. FRAMEWORKS AND INTERFACES ML for data scientists KERAS Frameworks Interfaces APPLICATION SERVICES ML for everyone PLATFORM SERVICES ML for engineers NVIDIA Tesla V100 GPUs (14x faster than P2) Machine Learning AMIs INFRASTRUCTURE Powering the ML Intel Xeon Skylake (Optimized for ML) AWS GREENGRASS ML L E X P O L L Y R E K O G N I T I O N I M A G E & V I D E O T R A N S C R I B E T R A N S L A T E C O M P R E H E N D F O R E C A S T P E R S O N A L I Z E AMAZON SAGEMAKER AWS DEEPLENS SAGEMAKER GROUND TRUTH & MECHANICAL TURK SPARK & EMR
  11. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Amazon SageMaker Build Train Deploy • Managed notebooks for authoring models • Templates for common ML applications • Built-in, high performance algorithms • Broad framework support • One-click training • Automatic model tuning • One-click deployment • Automatic A/B testing • Fully-managed hosting with auto scaling
  12. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Node with a value Neural Network recap linked to other nodes with various connection strengths. Each node value is based on how much of each connecting node’s signal arrives into it, plus some other value to decide what the final value will be. “Neuron” “Weights” “Bias” (1 * 2) + (5 * 3) + -4 = 13 2 3 1 5 -4 13 Example neuron with 2 inputs
  13. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Making A Custom Image Classifier In 21 Lines of Code
  14. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. 1. Group images by class name 2. Split images into training and test groups 3. Set some training parameters 4. Train and deploy our model 5. Classify images using our deployed model Creating our custom image classifier
  15. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Let’s look at the notebook in SageMaker…
  16. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Let’s try out our image classifier!
  17. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. More ML is built on AWS than anywhere else
  18. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Detecting the best images to use • Expedia have over 10 million images from 300,000 hotels • Using great images boosts conversion • They fine-tuned a pre-trained Convolutional Neural Network using 100,000 images • Hotel descriptions now automatically feature the best available images https://news.developer.nvidia.com/expedia-ranking-hotel-images- with-deep-learning/
  19. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Improving written text with Amazon SageMaker “Amazon SageMaker makes it possible for us to develop our TensorFlow models in a distributed training environment. (…) We can run inference on SageMaker itself, or if we need just the model, we download it from S3 and run inference of our mobile device implementations for iOS and Android customers.”
  20. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Where can I learn more?
  21. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Great places to get started with Deep Learning Machine Learning on AWS https://ml.aws 3Blue1Brown’s YouTube series on Neural Networks ~ 60 Minutes https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi Fast.ai’s Practical Deep Learning for Coders ~ 14 Hours http://www.fast.ai/ Neural Networks and Deep Learning, by Michael Neilsen ~ 6 Chapter Book http://neuralnetworksanddeeplearning.com/ These Demos - Jupyter Notebooks & Web Apps https://github.com/gabehollombe-aws/jupyter-notebooks https://github.com/gabehollombe-aws/webcam-s3-uploader https://github.com/gabehollombe-aws/webcam-sagemaker-inference
  22. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Machine Learning is for Everyone. What will you build?
  23. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark Thank you! Julio Faerman, Technical Evangelist @faermanj Gabe Hollombe, Technical Evangelist @gabehollombe