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

SIH_AWS_ML.pdf

 SIH_AWS_ML.pdf

AWS ML Introduction

Suman Debnath

February 04, 2020
Tweet

More Decks by Suman Debnath

Other Decks in Technology

Transcript

  1. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    AWS | Introduction to Machine Learning
    Suman Debnath,
    Principal Developer Advocate

    View Slide

  2. AI | ML | DL – Maybe a picture is better?
    Great Resource:
    The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World
    by Pedro Domingos

    View Slide

  3. 43,252,003,274,489,856,000
    43 QUINTILLION UNIQUE COMBINATIONS

    View Slide

  4. F2 U' R' L F2 R L' U'
    Learning
    function

    View Slide

  5. F2 U' R' L F2 R L' U'
    Learning
    function
    1%
    accuracy
    R U r U R U2 r U
    2%
    accuracy

    View Slide

  6. Learning
    function
    20%
    accuracy
    40%
    accuracy
    60%
    accuracy
    80%
    accuracy
    95%
    accuracy
    2%
    accuracy

    View Slide

  7. Learning
    function
    95%
    accuracy
    ?
    F2 R F R′ B′ D F D′ B D F

    View Slide

  8. SOLVED IN 0.9 SECONDS

    View Slide

  9. Don’t code the patterns
    Let the system
    Learn Through Data

    View Slide

  10. We Call This Approach Machine Learning

    View Slide

  11. Types Of Machine Learning

    View Slide

  12. Supervised Learning (depends on labeled datasets)
    Kid
    No, it’s a
    Labrador.

    View Slide

  13. Supervised Learning – How Machines Learn
    Human intervention and validation required
    e.g. Photo classification and tagging
    Input
    Label
    Machine
    Learning
    Algorithm
    Labrador
    Prediction
    Cat
    Training Data
    ?
    Label
    Labrador
    Adjust Model

    View Slide

  14. Unsupervised Learning (learning without labels)
    No human intervention required
    (e.g. Customer segmentation)
    Input
    Machine
    Learning
    Algorithm
    Prediction

    View Slide

  15. Machine Learning Use Cases
    Supervised Learning
    Ø Classification
    • Spam detection
    • Customer churn prediction
    Ø Regression
    • House price prediction
    • Demand forecasting
    Unsupervised Learning
    Ø Clustering
    • Customer segmentation
    There are other types as well
    (Reinforcement Learning, for example)
    but these two are the primary areas today

    View Slide

  16. AI/ML/DL Workflow
    Performance monitoring
    & adaptation
    8
    Data Acquisition & Storage
    1
    Model & Framework selection
    3
    Model Training
    4
    Hyper parameter tuning
    5
    Model testing and simulation
    6
    Model Deployment (inference)
    7
    Data Labelling
    2

    View Slide

  17. © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Machine Learning with AWS

    View Slide

  18. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    The AWS ML Stack
    Broadest and most complete set of Machine Learning capabilities
    VISION SPEECH TEXT SEARCH NEW CHATBOTS PERSONALIZATION FORECASTING FRAUD NEW DEVELOPMENT NEW CONTACT CENTERS
    NEW
    Amazon SageMaker Ground
    Truth
    Augmented
    AI
    SageMaker
    Neo
    Built-in
    algorithms
    SageMaker
    Notebooks NEW
    SageMaker
    Experiments NEW
    Model
    tuning
    SageMaker
    Debugger NEW
    SageMaker
    Autopilot NEW
    Model
    hosting
    SageMaker
    Model Monitor NEW
    Deep Learning
    AMIs & Containers
    GPUs &
    CPUs
    Elastic
    Inference
    Inferentia FPGA
    Amazon
    Rekognition
    Amazon
    Polly
    Amazon
    Transcribe
    +Medical
    Amazon
    Comprehend
    +Medical
    Amazon
    Translate
    Amazon
    Lex
    Amazon
    Personalize
    Amazon
    Forecast
    Amazon
    Fraud Detector
    Amazon
    CodeGuru
    AI SERVICES
    ML SERVICES
    ML FRAMEWORKS & INFRASTRUCTURE
    Amazon
    Textract
    Amazon
    Kendra
    Contact Lens
    For Amazon Connect
    SageMaker Studio IDE NEW
    NEW
    NEW
    NEW
    NEW

    View Slide

  19. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    The AWS ML Stack
    Broadest and most complete set of Machine Learning capabilities
    VISION SPEECH TEXT SEARCH NEW CHATBOTS PERSONALIZATION FORECASTING FRAUD NEW DEVELOPMENT NEW CONTACT CENTERS
    NEW
    Amazon SageMaker Ground
    Truth
    Augmented
    AI
    SageMaker
    Neo
    Built-in
    algorithms
    SageMaker
    Notebooks NEW
    SageMaker
    Experiments NEW
    Model
    tuning
    SageMaker
    Debugger NEW
    SageMaker
    Autopilot NEW
    Model
    hosting
    SageMaker
    Model Monitor NEW
    Deep Learning
    AMIs & Containers
    GPUs &
    CPUs
    Elastic
    Inference
    Inferentia FPGA
    Amazon
    Rekognition
    Amazon
    Polly
    Amazon
    Transcribe
    +Medical
    Amazon
    Comprehend
    +Medical
    Amazon
    Translate
    Amazon
    Lex
    Amazon
    Personalize
    Amazon
    Forecast
    Amazon
    Fraud Detector
    Amazon
    CodeGuru
    AI SERVICES
    ML SERVICES
    ML FRAMEWORKS & INFRASTRUCTURE
    Amazon
    Textract
    Amazon
    Kendra
    Contact Lens
    For Amazon Connect
    SageMaker Studio IDE NEW
    NEW
    NEW
    NEW
    NEW

    View Slide

  20. © 2020, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
    Vision: Amazon Rekognition
    Key Features
    Object & Scene Detection
    Image Moderation
    Facial Analysis
    Facial Comparison
    Facial Recognition
    Celebrity Recognition

    View Slide

  21. © 2020, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
    Amazon Polly
    “The temperature
    in Brussels is 15°C”
    “The temperature
    in Brussels is 15 degrees
    Celsius”
    Speech: Amazon Polly
    Text in; lifelike speech out
    Key Features
    • 60+ Voices
    • 25+ Languages
    • Lip-Syncing & Text Highlighting
    • Fine-grained Voice Control
    • Custom Vocabularies

    View Slide

  22. © 2020, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
    Speech: Amazon Transcribe
    Automatic Speech Recognition
    Time
    stamps
    Support for
    both regular &
    telephony audio
    Punctuation
    &
    formatting
    S3
    integration
    Recognize
    multiple
    speakers
    Custom
    dictionaries
    ? !

    View Slide

  23. © 2020, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
    Text: Amazon Comprehend
    Natural Language Processing
    Sentiment Entities Languages
    Key phrases Topic modeling

    View Slide

  24. © 2020, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
    Text: Amazon Comprehend
    Extract insights from text
    Amazon.com, Inc. is located in
    Seattle, WA and was founded
    July 5th, 1994 by Jeff Bezos. Our
    customers love buying everything
    from books to blenders at great
    prices
    Named Entities
    - Amazon.com: Organization
    - Seattle, WA: Location
    - July 5th,1994: Date
    - Jeff Bezos: Person
    Keyphrases
    - Our customers
    - books
    - blenders
    - great prices
    Sentiment
    Positive
    Language
    English

    View Slide

  25. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
    © 2020, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Trademark
    The AWS ML Stack
    Broadest and most complete set of Machine Learning capabilities
    VISION SPEECH TEXT SEARCH NEW CHATBOTS PERSONALIZATION FORECASTING FRAUD NEW DEVELOPMENT NEW CONTACT CENTERS NEW
    Amazon SageMaker Ground
    Truth
    Augmented
    AI
    SageMaker
    Neo
    Built-in
    algorithms
    SageMaker
    Notebooks NEW
    SageMaker
    Experiments NEW
    Model
    tuning
    SageMaker
    Debugger NEW
    SageMaker
    Autopilot NEW
    Model
    hosting
    SageMaker
    Model Monitor NEW
    Deep Learning
    AMIs & Containers
    GPUs &
    CPUs
    Elastic
    Inference
    Inferentia FPGA
    Amazon
    Rekognition
    Amazon
    Polly
    Amazon
    Transcribe
    +Medical
    Amazon
    Comprehend
    +Medical
    Amazon
    Translate
    Amazon
    Lex
    Amazon
    Personalize
    Amazon
    Forecast
    Amazon
    Fraud Detector
    Amazon
    CodeGuru
    AI SERVICES
    ML SERVICES
    ML FRAMEWORKS & INFRASTRUCTURE
    Amazon
    Textract
    Amazon
    Kendra
    Contact Lens
    For Amazon Connect
    SageMaker Studio IDE NEW
    NEW
    NEW
    NEW
    NEW

    View Slide

  26. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker |

    View Slide

  27. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Adjust
    Iterate

    View Slide

  28. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Ground Truth Notebooks Training Inference
    Amazon SageMaker
    Build, train, and deploy machine learning models quickly
    Adjust
    Iterate

    View Slide

  29. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker
    AWS Console Dashboard

    View Slide

  30. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker
    Build, train, and deploy machine learning models quickly
    Adjust
    Iterate
    Ground Truth Notebooks Training Inference

    View Slide

  31. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker |
    Easy instructions for human labeling

    View Slide

  32. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker
    Build, train, and deploy machine learning models quickly
    Adjust
    Iterate
    Ground Truth Notebooks Training Inference

    View Slide

  33. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker |
    • Jupyter notebooks
    • Support Jupyter Lab
    • Multiple built-in kernels
    • Bring your own kernels
    • Integrate with Git
    • Sample notebooks

    View Slide

  34. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker
    Build, train, and deploy machine learning models quickly
    Adjust
    Iterate
    Ground Truth Notebooks Training Inference

    View Slide

  35. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker |
    More than 300 example notebooks
    • ML Introduction
    • Advanced functionality
    • Hyper parameter optimization
    • Reinforcement learning
    • Ground Truth
    • Neo
    • Python SDK
    • Tensorflow
    • Mxnet
    • Pytorth
    • FastAI

    View Slide

  36. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker |
    Amazon
    SageMaker
    Dev desktops
    SageMaker Environment
    SageMaker
    Notebook
    EC2
    EC2
    EC2
    Training
    Inference
    Control plane (create notebook, start training, … )
    Data plane

    View Slide

  37. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    One click in Console
    Using API/SDK
    - OR -
    Launch
    Training
    Amazon SageMaker |

    View Slide

  38. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker |
    Estimators: Encapsulate training on SageMaker.
    Models: Encapsulate built ML models.
    Predictors: Provide real-time inference and transformation
    using Python data-types against a SageMaker endpoint.
    Session: Provides a collection of methods for working with
    SageMaker resources.
    SageMaker Python SDK

    View Slide

  39. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker |
    Built-in algorithms
    XGBoost, Linear
    Learner
    K-means, K-nearest
    Neighbors, PCA,
    Obejct2vec,
    BlazingText
    Image classification,
    Object detection,
    semantic
    segmentation
    LDA and NTM for
    topic modeling,
    seq2seq for
    translation
    Random Cut Forest,
    IP insights
    Regression and
    Classification
    Clustering and
    pre-processing
    Computer
    Vision
    Text and
    documents
    Anomaly
    detection
    Forecasting and
    Recommendations
    DeepAR and
    Factorization
    Machines

    View Slide

  40. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Amazon SageMaker
    Build, train, and deploy machine learning models quickly
    Adjust
    Iterate
    Ground Truth Notebooks Training Inference

    View Slide

  41. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Hosting
    Services
    Batch
    Transform
    Elastic
    Inference
    Trained Model
    Neo
    Run
    Anywhere DeepRacer
    Amazon SageMaker |
    DeepLens
    Marketplace

    View Slide

  42. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Practical education on ML for new & experienced practitioners
    Based on the same material used to train Amazon developers
    To learn more:
    AWS Machine Learning University

    View Slide

  43. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    ml.aws

    View Slide

  44. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Free AWS

    View Slide

  45. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    /suman-d /_sumand

    View Slide

  46. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark
    © 2020 Amazon Web Services, Inc. or its affiliates. All rights reserved |
    Thank You

    View Slide