Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Machine Learning and AI


Published on

The breath and depth of Azure products that fall under the AI and ML umbrella can be difficult to follow. In this presentation I’ll first define exactly what AI, ML, and deep learning is, and then go over the various Microsoft AI and ML products and their use cases.

Published in: Technology
  • The Surprising Reason 11:11 Keeps Appearing. Free report reveals hidden messages from the Universe to unlock success, wealth... even true love. Claim your copy and reveal your messages now! ■■■
    Are you sure you want to  Yes  No
    Your message goes here
  • Nine Signs Wealth is Coming Your Way... 
    Are you sure you want to  Yes  No
    Your message goes here
  • Unlock Her Legs(Official) $69 | Get 90% Off + 8 Special Bonus? ●●●
    Are you sure you want to  Yes  No
    Your message goes here
  • Free Healing Soundscape - Just click "Play" to immerse yourself in a beautiful "Sound Bath" that clears negativity, awakens abundance, and brings miracles into your life! Listen for yourself right now. ♣♣♣
    Are you sure you want to  Yes  No
    Your message goes here
  • New $31,515 USD profit system revealed. using an automated software that predicts the winners for Soccer, Horse racing and even major sports such as NBA, NFL, NHL, MLB! ➤➤
    Are you sure you want to  Yes  No
    Your message goes here

Machine Learning and AI

  1. 1.
  2. 2. Machine learning is a data science technique that allows computers to use existing data to forecast future behaviors, outcomes, and trends.
  3. 3. Enterprise AI Maturity Model Foundational Wrong expectations or disappointment Low digitization Basic analytical capabilities Questioning what AI is and how to apply it Approaching Digitization underway Looking to increase or optimize processes Cautious about disruption Hopeful on AI and its promise Aspirational High digitization Desires new business models Achieved a data culture Experimented and applied AI Mature Understands model lifecycle Building a foundational data architecture Emerging data science and operational capability
  4. 4. © Microsoft Corporation Helping you innovate across your business Customer insights Sales insights Virtual assistants Cash flow forecasting HR insights Churn analytics Dynamic pricing Waiting line optimization Risk management Quality assurance Resource planning Lead scoring Intelligent chatbots Financial forecasting Employee insights Marketing Sales Service Finance Operations Workforce Product recommendationProduct recommendation Predictive maintenancePredictive maintenance Demand forecastingDemand forecasting
  5. 5. © Microsoft Corporation Advanced analytics pattern in Azure Azure Data Lake store Azure Storage HDInsightAzure Databricks Azure ML service ML server Model training Long-term storage Data processing Azure Data Lake Analytics Azure ML Studio SQL Server (in-database ML) Azure Databricks (Spark ML) Data Science VM Cosmos DB Serving storage SQL DB SQL DW Azure Analysis Services Cosmos DB Batch AI SQL DB Azure Data Factory Orchestration Azure Container Service Trained model hosting SQL Server (in-database ML) Data collection and understanding, modeling, and deployment Sensors and IoT (unstructured) Logs, files, and media (unstructured) Business/custom apps (structured) Applications Dashboards Power BI
  6. 6. Azure Machine Learning Studio
  7. 7. © Microsoft Corporation Azure machine learning studio Use Azure Machine Learning to deploy your model into production as a web service in minutes Work with familiar coding languages such as R and Python while benefitting from hundreds of built-in packages and support for custom code Deploy models to production as web services that can be called from any device, anywhere, using any data source Easily share your solution with the world on the Azure Marketplace A fully-managed cloud service that enables you to easily build, deploy and share predictive analytics solutions
  8. 8. AZURE MACHINE LEARNING STUDIO Platform for emerging data scientists to graphically build and deploy experiments • Rapid experiment composition • > 100 easily configured modules for data prep, training, evaluation • Extensibility through R & Python • Serverless training and deployment Some numbers: • 100’s of thousands of deployed models serving billions of requests
  9. 9.
  10. 10. Data Science Virtual Machines (DSVM)
  11. 11. Data Science Virtual Machines
  12. 12. Azure Machine Learning service
  13. 13. WHAT IS AZURE MACHINE LEARNING SERVICE? Set of Azure Cloud Services Python SDK  Prepare Data  Build Models  Train Models  Manage Models  Track Experiments  Deploy Models That enables you to:
  14. 14. Workspace – Top level container for model management and experimentation. Also, creates and manages storage, container registry, key vault and app insights Experiments – Grouping of training runs for a given script Pipelines – Stitch together multiple stages to create machine learning workflows Compute – Compute resources for training or image deployment Models – Encapsulation of trained models Images – Docker images containing trained models to be deployed to a compute target Deployments – Deployment of an image to web services, IoT Edge and FPGAs Data Stores – Abstraction layer over Azure storage Azure Machine Learning service features
  15. 15. Custom AI Typical E2E Process … Prepare Experiment Operationalize/Deploy Orchestrate Azure Databricks Machine Learning Compute Data Science Virtual Machine Azure ML service Azure Container Instances Azure Kubernetes ServiceAzure Databricks Azure Data Factory
  16. 16. Azure ML Concept Model Management Model Management in Azure ML usually involves these four steps Step 1: Step 2: Step 3: Step 4:
  17. 17. Azure ML Artifact Compute Target Compute Target Training Deployment Local Computer ✓ A Linux VM in Azure (such as the Data Science Virtual Machine) ✓ Azure ML Compute ✓ Azure Databricks ✓ Azure Data Lake Analytics ✓ Apache Spark for HDInsight ✓ Azure Container Instance ✓ Azure Kubernetes Service ✓ Azure IoT Edge ✓ Field-programmable gate array (FPGA) ✓ Currently supported compute targets
  18. 18. Azure ML service Artifacts Image and Registry Image contains Two types of images Image Registry
  19. 19. Azure ML Artifact Deployment Deployment is an instantiation of an image. Two options: Web service IoT Module
  20. 20. Why Intelligent Edge? High-speed data processing, analytics and shorter response times are more essential than ever. Intelligent Cloud • Business agility and scalability: unlimited computing power available on demand. Intelligent Edge • Can handle priority-one tasks locally even without cloud connection. • Can handle generated data that is too large to pull rapidly from the cloud. • Enables real-time processing through intelligence in or near to local devices. • Flexibility to accommodate data privacy related requirements.
  21. 21. Azure ML service Lets you easily implement this AI/ML Lifecycle Azure Machine Learning Workflow Steps
  22. 22. Azure ML: How to deploy models at scale
  23. 23. Services + Customer journey Data Prep Build and Train Manage and Deploy Apache Spark / Big Data Python ML developer Azure ML service (Pandas, NumPy etc. on AML Compute) Azure ML service (OSS frameworks, Hyperdrive, Pipelines, Automated ML, Model Registry) Azure ML service (containerize, deploy, inference and monitor) Azure ML service (containerize, deploy, inference and monitor) Azure Databricks (Apache Spark Dataframes, Datasets, Delta, etc.) Azure Databricks + Azure ML service (Spark MLib and OSS frameworks + Automated ML, Model Registry)
  24. 24. Comparable Table Azure Machine Learning Studio Azure Machine Learning Services Pros • Rapid development (Drag and Drop) • Works well with relatively simple datasets • Pre-built ML algorithms • Cheap • Fast (VMs with GPUs) • Different optimization methods, CI/CD pipeline • Full control during training • Manage computing resources (choose VM size) • Use open source ML libraries Cons • Can be slow • Limited optimization methods, operationalized architecture • Less control during training • Fixed computing resources • More elaborate to build, require deeper knowledge of machine learning • Deeper models need much more data with much more memory • Higher costs for VM with GPU
  25. 25. Azure Databricks Databricks Spark as a managed service on Azure
  26. 26. Azure Databricks key audiences & benefits Unified analytics platform Integrated workspace Easy data exploration Collaborative experience Interactive dashboards Faster insights • Best Spark & serverless • Databricks managed Spark Improved ETL performance • Zero management clusters, serverless Easy to schedule jobs Automated workflows Enhanced monitoring & troubleshooting • Automated alerts & easy access to logs Zero Management Spark Cluster democratization (serverless) Fast, collaborative analytics platform accelerating time to market No dev-ops required Enterprise grade security • Encryption • End-to-end auditing • Role-based control • Compliance Data scientist Data engineer CDO, VP of analytics Provided by Microsoft and Databricks under NDA
  27. 27. A Z U R E D A T A B R I C K S Microsoft Azure
  28. 28. A Z U R E D A T A B R I C K S C O R E A R T I F A C T S Azure Databricks
  29. 29. P R O V I S I O N I N G A Z U R E D A T A B R I C K S W O R K S P A C E
  30. 30. © Microsoft Corporation Comparing Notebooks in Azure Databricks against other IDEs Data understanding services Notebooks in Azure Databricks Other IDEs No Azure Databricks only Yes Spark Python, Scala, R, SQL, Bash Shell Provides extensive visualizations library in addition to supporting 3rd party libraries. Full Azure Active Directory integration Simultaneous, multi-user collaboration Yes GitHub, Bitbucket Requires software installation Yes Pieced together, disparate solutions No Python, PySpark Python, SQL, Bash Shell Supports standard Jupyter Notebook visualizations and libraries like Matplotlib No No No Yes, but not optimal Execution environment Serverless service Kernels supported Languages supported Visualizations Supports role-based access control Collaborative workspaces Run notebooks as scheduled jobs Source control
  31. 31. M I X I N G L A N G U A G E S I N N O T E B O O K S You can mix multiple languages in the same notebook Normally a notebook is associated with a specific language. However, with Azure Databricks notebooks, you can mix multiple languages in the same notebook. This is done using the language magic command: • %python Allows you to execute python code in a notebook (even if that notebook is not python) • %sql Allows you to execute sql code in a notebook (even if that notebook is not sql). • %r Allows you to execute r code in a notebook (even if that notebook is not r). • %scala Allows you to execute scala code in a notebook (even if that notebook is not scala). • %sh Allows you to execute shell code in your notebook. • %fs Allows you to use Databricks Utilities - dbutils filesystem commands. • %md To include rendered markdown
  32. 32. © Microsoft Corporation For Cloud environments Train and evaluate machine learning architecture Raw data Reference data • 0 1 Machine learning Azure Databricks Scale out clusters Azure Databricks Operational stores Data warehouse SQL DW Cosmos DB Model MGMT, experimentation, and run history Azure ML Service (preview) Azure ML service (preview)
  33. 33. © Microsoft Corporation Fast, easy, and collaborative Apache Spark™-based analytics platform Azure Databricks for machine learning modeling Tools InfrastructureFrameworks Provision autoscaling clusters on-demandUse best-in-class notebooks to quickly access model performance and revert when needed TensorFlow, Keras, and XGBoost, all installed and configured for Spark clusters Enable distributed, multi-GPU training with Horovod via a native runtime Get seamless updates of the Spark stack to ensure uninterrupted operations Capture model telemetry at every stage to enable reproduceable results Schedule notebook activities as jobs in and let Azure Data Factory orchestrate the rest Take advantage of Azure ML Services to for simple Kubernetes Cluster deployments Leverage parallelized ML algorithms from battle-tested libraries
  34. 34. © Microsoft Corporation Build in your environment of choice Custom IDEs Visual studio tools for AINotebooksR studio PyCharm
  35. 35. S P A R K M A C H I N E L E A R N I N G ( M L ) O V E R V I E W  Offers a set of parallelized machine learning algorithms (see next slide)  Supports Model Selection (hyperparameter tuning) using Cross Validation and Train-Validation Split.  Supports Java, Scala or Python apps using DataFrame-based API (as of Spark 2.0). Benefits include: • An uniform API across ML algorithms and across multiple languages • Facilitates ML pipelines (enables combining multiple algorithms into a single pipeline). • Optimizations through Tungsten and Catalyst • Spark MLlib comes pre-installed on Azure Databricks • 3rd Party libraries supported include: H20 Sparkling Water, SciKit- learn and XGBoost Enables Parallel, Distributed ML for large datasets on Spark Clusters
  36. 36. M M L S P A R K Microsoft Machine Learning Library for Apache Spark (MMLSpark) lets you easily create scalable machine learning models for large datasets. It includes integration of SparkML pipelines with the Microsoft Cognitive Toolkit and OpenCV, enabling you to:  Ingress and pre-process image data  Featurize images and text using pre-trained deep learning models  Train and score classification and regression models using implicit featurization
  37. 37. S P A R K M L A L G O R I T H M S Spark ML Algorithms
  38. 38. D E E P L E A R N I N G  Supports Deep Learning Libraries/frameworks including: • Microsoft Cognitive Toolkit (CNTK) • TensorFlow • Keras • Theano  Offers Spark Deep Learning Pipelines, a suite of tools for working with and processing images using deep learning using transfer learning. It includes high-level APIs for common aspects of deep learning so they can be done efficiently in a few lines of code: Azure Databricks supports and integrates with a number of Deep Learning libraries and frameworks to make it easy to build and deploy Deep Learning applications Distributed Hyperparameter Tuning Transfer Learning
  39. 39. D E E P L E A R N I N G P I P E L I N E S   Transfer Learning APIs for common aspects of deep learning so they can be done efficiently in a few lines of code  Transfer Learning
  40. 40. T R A N S F E R L E A R N I N G  ImageNet –  InceptionV3 – Created @ Google Brain  Xception – François Chollet  ResNet50 – ImageNet Large Scale Visual Recognition Competition  VGG16/VGG19 – Introduced in 2014. This network is characterized by its simplicity, using only 3×3 convolutional layers stacked on top of each other. The 16 and 19 stand for the number of weight layers in the network. VGG stands for Visual Geometry Group. Pre-Trained Libraries
  41. 41. Ready to use clusters with built-in ML Frameworks HorovodEstimator for simplified distributed training on TensorFlow with Apache Spark GPU support 49
  42. 42. A D V A N C E D A N A L Y T I C S O N B I G D A T A INGEST STORE PREP & TRAIN MODEL & SERVE Cosmos DB Business/custom apps (structured) Files (unstructured) Media (unstructured) Logs (unstructured) Azure Data Lake Store Gen2Azure Data Factory Azure SQL Data Warehouse Azure Analysis Services Power BI PolyBase SparkR Azure Databricks Microsoft Azure also supports other Big Data services like Azure HDInsight, Azure Machine Learning to allow customers to tailor the above architecture to meet their unique needs. Real-time apps
  43. 43. © Microsoft Corporation Operationalization and management architecture Scale out clusters Notebooks Azure Databricks Containers AKS ACI IoT edge Intelligent Apps Power BI Docker Model MGMT, experimentation, and run history Azure ML service (Preview) Data warehouse SQL DW Operational stores Cosmos DB
  44. 44. C L I C K T O E D I T M A S T E R T I T L E S T Y L E
  45. 45. B I G D A T A S C A L E W I T H M I C R O S O F T M L S E R V E R f(x) Task Task Task  Full support for R and Python  Scale via parallel & distributed computation  On-premises deploys to multiple platforms:  Machine Learning Server for Hadoop  Machine Learning Server for Linux  Machine Learning Server for Windows  In Azure, available within:  ML Server on HDInsight (Hadoop + Spark)  Machine Learning Server on Linux VM  Data Science VM (Linux and Windows)  ML Server provides the underlying functionality integrated into SQL Server as Machine Learning Services (In-Database), which is available to:  All editions of SQL Server 2017  It is also available in Azure SQL Database
  46. 46. Machine Learning Server at a glance Platforms & Data Tools Languages Algorithms Data Sources Rattle Mrsdeploy RESTful API deployment Real-Time Scoring Visualization Tool Integration .csv Microsoft .XDF In-database deployment Operationalization Distributed Parallelized Algorithms: •RevoScaleR library •MicrosoftML library •Custom parallelization frameworks Open source R algorithms & visualizations: •CRAN •bioconductor Plus: •Deep Learning •Pretrained Models •Prebuilt Featurizers ODBC/JDBC
  47. 47. ML Server for Hadoop/Spark: In-memory, massive parallelism User Workstation ML Server for Hadoop Data Frames YARN Resource Management Spark Executor Worker Task Spark Executor Worker Task Spark Executor Worker Task .csv, xdf, hive, parquet, ORC ScaleR Master Task Finalize r Initiator Edge Node Spark Driver Ver. 1.6 or 2.0 ML Server components installed
  48. 48. In-database analytics with SQL Server 2017
  49. 49. Build intelligent apps and AI with all your data Analyzing all data Easily and securely manage data big and small Managing all data Simplified management and analysis through a unified deployment, governance, and tooling Unified access to all your data with unparalleled performance Integrating all data
  50. 50. Including Relational, noSQL, Hadoop Using Spark and SQL With Azure Data Studio
  51. 51. SQL Server 2019 big data, analytics, and AI Managed SQL Server, Spark, and data lake Store high volume data in a data lake and access it easily using either SQL or Spark Management services, admin portal, and integrated security make it all easy to manage SQL Server Data virtualization Combine data from many sources without moving or replicating it Scale out compute and caching to boost performance T-SQL Analytics Apps Open database connectivity NoSQL Relational databases HDFS Complete AI platform Easily feed integrated data from many sources to your model training Ingest and prep data and then train, store, and operationalize your models all in one system SQL Server External Tables Compute pools and data pools Spark Scalable, shared storage (HDFS) External data sources Admin portal and management services Integrated AD-based security SQL Server ML Services Spark & Spark ML HDFS REST API containers for models
  52. 52. Compute pool SQL Compute Node SQL Compute Node SQL Compute Node … Compute pool SQL Compute Node IoT data Directly read from HDFS Persistent storage … Storage pool SQL Server Spark HDFS Data Node SQL Server Spark HDFS Data Node SQL Server Spark HDFS Data Node Kubernetes pod Analytics Custom apps BI SQL Server master instance Node Node Node Node Node Node Node SQL Data mart SQL Data Node SQL Data Node Compute pool SQL Compute Node Storage Storage
  53. 53. Learn more. R
  54. 54. Integration with Azure services Azure and Power BI have the built-in connectivity and integration to bring business intelligence efforts to life Integration can be achieved without the need to develop complex solutions:  Direct connect:  Azure SQL Database  Azure SQL Data Warehouse  Spark on Azure HDInsight  Power BI Desktop  Real-time dashboards with Azure Stream Analytics HDInsight Storage Event Hubs Machine Learning SQL Server Stream Analytics Power BI
  55. 55. Integration with Azure services Power BI Desktop Connect to various Azure services, and create queries  Queries can be integrated with other data source types, not necessarily Azure  Datasets sourced from a Power BI Desktop file can be refreshed
  56. 56. Integration with Azure services Real-time dashboards with Azure Stream Analytics Use Azure Stream Analytics to push live, streaming data to Power BI  Enables real-time dashboards at scale, over data from devices and applications  Can stream millions of events per second  Can perform aggregation over time windows
  57. 57. Integration with Azure services Advanced analytics Coalesce Azure services together to drive advanced analytics:  Azure HDInsight: Big Data processing  Azure Machine Learning: Predictive analytics  Azure Data Factory: Orchestration at scale
  58. 58. Describing additional capabilities Running R and Python scripts R Python scripts can be ran directly in Power BI Desktop, and resulting datasets imported into a Power BI Desktop data model  R, Python must be installed on the local machine  Only data frames are imported  Columns typed as Complex and Vector are not imported  Can be refreshed with a gateway
  59. 59. Describing additional capabilities Generating R and Python visuals R and Python visuals render from R script, accepting input fields Benefits:  Leverage the voluminous and growing number of out-of- the-box plots available in R and Python  Easily customize R and Python visuals by developing the script  Combine advanced analytics in visuals  Interact with R and Python visuals in Power BI Desktop (filter, and cross-filter are supported)
  60. 60. Transform your data Using R or Python
  61. 61. Point and click to explain the increase/decrease Data transformations “by example” Relationship and data type detection Built in integration with R and Python
  62. 62. Power BI AutoML
  63. 63. The flow suggests default set of inputs for the ML model, including those from related entities in the Dataflow.
  64. 64. • The model accuracy preview report includes the top influencers for the model, including a breakdown of how the different values for that influencer affects the outcome.
  65. 65.
  66. 66. Role of Cognitive Services making it easier to infuse AI frameworks TensorFlow KerasPytorch Onnx ML Extract intent Detect empty shelvesExtract identity generic specialized effort pioneer expert developer everyone Pre-built, customizable services face OCR text vision speech translation QnA ...... use case featuresF1 F2 F3 F4 how deep in the stack?
  67. 67. Cognitive Services capabilities Infuse your apps, websites, and bots with human-like intelligence
  68. 68. A variety of real-world applications Vision Speech Intent: PlayCall Language Knowledge Search
  69. 69. Face Detection Face API detects up to 64 human faces with high precision face location in an image. And the image can be specified by file in bytes or valid URL. Face Recognition Face recognition is widely used in many scenarios including security, natural user interface, image content analysis and management, mobile apps, and robotics. Four face recognition functions are provided: face verification, finding similar faces, face grouping, and person identification. Key features: • Detect human faces and compare similar ones • Organize images into groups based on similarity • Identify previously tagged people in images Vision – Face Azure Cognitive Services
  70. 70. Visual Intelligence Made Easy Easily customize your own state-of-the-art computer vision models that fit to your unique use case. Just bring a few examples of labeled images and let Custom Vision do the hard work. Custom Vision Azure Cognitive Services
  71. 71. Speech Azure Cognitive Services For optimal result in Speech to Text, customize: • acoustic models for your use environments, such as vehicles • field-specific vocabulary and grammar, such as medical or IT • pronunciation of abbreviations and acronyms, such as "IOU" for "I owe you." • Speaker Recognition • Speech to Text • Text to Speech
  72. 72. LUIS – Language Understanding Azure Cognitive Services LUIS aims to be the most comprehensive cloud-based service for conversational understanding, and the easiest to use for developers with no AI expertise: • extracts intent/action and entities from user utterances • includes dictionaries, which can be extended with customer-specific terms Roadmap highlights coming up: • 2H2018 easier to use together with Azure Bot, Speech and QnA Maker services
  73. 73. Q&A QnA Maker Azure Cognitive Services Microsoft & NDA Customers only—do not share
  74. 74. Extract insights from customer feedback and social network postings. I had a wonderful trip to Seattle and enjoyed seeing the Space Needle! • submit up to 100 calls per minute, each with up to 1,000 documents of up to 5,000 characters each Links backed by Wikipedia in select languages Text Analytics Azure Cognitive Services
  75. 75. translate dynamic content in your mobile, desktop and web apps  automatically detect languages  transliterate into different alphabets Text Translator – Translation Azure Cognitive Services 60+ supported languages:
  76. 76. Resources: • Blog • Case Study • Documentation • Samples Content Moderator Azure Cognitive Services Content Moderator helps businesses manage risks associated with user generated content (UGC) by using machine-assisted content moderation APIs and a human review tool. Features include:  Detection of potential adult, racy, and offensive, illegal, and unwanted image & video content  Identification of possible profanity and undesirable text  Built-in human review tool for improving the results  Workflows that allow you to add other API’s and extract more content insights Customers using Content Moderator technologies include:  Online marketplaces/e-Commerce sites for moderating catalogs and chatbots  Social media/messaging/gaming platforms for moderating user content and digital assets  Enterprises/K-12 solution providers moderating user content and information chatbots  Global content moderation service providers using AI to augment human moderation teams
  77. 77. Bing Search Azure Cognitive Services
  78. 78. – Ingest paper – Identify customers and staff – Customer care – Customer understanding
  79. 79. ? Searchable content image + markup { “Bank Statement": [ { “bank”: “Rural Bank”, “acc name”: “Joe Sample”, “opening”: { “balance”: $7,701.18”, “date”: “01/02/2011” } “deposits”: “$70,062.31” … }] } Applications • • • •  
  80. 80. example Solution Architecture Custom Vision tuned for docs training live ops learned parameters Doc classifier (per industry) ... pre-processor tagged extraction mask Form extractors (10s-100s per industry) ... Domain expert describes regions for extraction (1 per doc class) SSN: ###-##-#### Income: #######.## ... ... 1000’s – millions of docs per company { “W2 Tax Form": { “year”: “2018”, “name”: “Joe Sample”, “address”: { “number”: “921”, “street”: “Getaway Lane” } “1 Wages”: “$77,500.34” … } } Markup Content ...
  81. 81. Applications • • • •   train identities live ops Face Verify EmotionSpeaker Verify Assess and react: • • "disgust": 0.6847, "sadness": 0.2135, "anger": 0.0955… "happy": 0.999…  "happy": 0.992… Extra security: •  
  82. 82. Applications • • • •   pass if needed, provide context $$$ chasm
  83. 83. no-code management Azure Search Fuzzy matching + QnA Maker live ops Azure Indexing + QnA Editor QnA Maker Knowledgebase (KB) FAQs, user manuals channels:
  84. 84. training live ops Operations live data Stores Products Policies QnA Maker QnA Maker QnA Maker Products KB Stores KB ... ... Operation utterances LUIS LUIS Intent Classifier One intent: - per KB - per Operation natural language documents( ) dispatch on intent ...
  85. 85. live ops QnA Maker KB ... Operations as needed Azure Bot ... intent + entities troubleshoot Sentiment Analysis red flag LUISLanguage Detection Translation as needed Speech to Text Text to Speech
  86. 86. QnA Ma ... Operati Azure Bot ... Annotated logs: + sentiment + intent + entities Applications • •  Key phrase extraction Speech to Text Recordings (archival) troubleshoot Sentiment Analysis Social Media Reviews Voice of Customer Evolve: • • •
  87. 87. Automated Machine Learning (in Machine Learning Services)
  88. 88. What is automated machine learning?
  89. 89. © Microsoft Corporation AutoML
  90. 90. Azure Automated ML Current Capabilities Category Value Compute Target
  91. 91. Web UI [Azure portal - Preview] Private Preview - 2/11 •Getting started experience •Start an automated ml training job on your data (upload/Blob) •Explore data •View progress and results for training job and each iteration •View automated ML dashboard for an overview Public Preview - April 2019 •Set advanced settings for the training job •Forecasting support •Automatically deploy a model •Advanced data exploration (visualizations, correlations, etc.) •View model Explainability •Support additional 1p data sources (e.g. Azure SQL, ADLS, …) May 2019 – General Availability •Apply data transformations •Support additional 1p & 3p data source •Continue experiment in Jupyter Notebook Microsoft confidential (NDA) Create automated ML experiments from UI only (“no code”) • Get started with ML quickly • Powered by the automated ML SDK – easily customize advanced settings • Automate the end-to-end ML workflow from the UI • Easily explore and monitor all your experiments from a single place Roadmap
  92. 92. “Day 0” (First time) experience Create your first experiment with automated machine learning to produce quality models with zero effort Automate the process of algorithm selection, hyperparameter tuning, and best model selection with automated machine learning, and accelerate your productivity. Select your data and let automated ML do the rest to provide the best model from endless possible options
  93. 93. Create a new automated machine learning experiment * Training compute  amlcompute-4a57de20b3f1 Next * Experiment name myfirstautomlexperiment Cancel Create new
  94. 94. Create a new automated machine learning experiment * Training compute  Select existing… * Experiment name myfirstautomlexperiment Create new Select a file from Azure blob storage account Data Preview Data Profile Include in training Include in training Include in training Include in training Include in training Include in training Include in training Include in training Use first row as header Select a storage account and a container to view the files list mytestmlexperimentsto… automl-blob-d8b2d4df-…* Storage account * Container
  95. 95. Include in training Include in training Include in training Include in training Include in training Include in training Include in training Include in training Data Preview Data Profile Training job settings: * Training job type  Classification * Target column  Freight cost * Primary metric  Accuracy Number of iterations: 100
  96. 96. Include in training Include in training Include in training Include in training Include in training Include in training Include in training Include in training Data Preview Data Profile Training job settings: * Training job type  Classification * Target column  Freight cost * Primary metric  Accuracy Number of iterations: 100 Data Preview Data Profile Condensed view
  97. 97. Training job settings: * Training job type  Classification * Target column  Freight cost * Primary metric  Accuracy Number of iterations: 100 StartCancel
  98. 98. Myfirstautomlexperiment | Run #XXX
  99. 99. Automated machine learning dashboard # Running # Completed # Failed # Cancelled “Day 30” experience 0 5 10 15 Run status history (All) Cancelled Failed Completed Running All dates
  100. 100. © Microsoft Corporation A side-by-side comparison of capabilities and features Model deployment options Scoring interface provided Deployment environments Scalability of scoring interface Scoring requirements Model packaging SQL Server or SQL Database T-SQL stored procedure SQL Server 2017 database instance on-premises or in Azure VM Need to author Python or R code within a T-SQL stored procedure that loads the trained model from a table where it is stored and applies it in scoring. Serialized to table Limited to capacity of single server Azure Databricks Notebook or Job Load the trained model from storage and apply to scoring in notebook in Python, Scala, R, or SQL. Serialized to storage Azure Databricks cluster, model export Can scale across cluster resources Web service Create a Docker image that contains scoring service, model, and dependencies Docker image SQL Server, Hadoop Scales by deploying more instances in Azure Container Services Azure Machine Learning AKS, ACI edge via AML IoT, IoT edge via AML AKS, ACI IoT, IoT edge Spark and Batch AI
  101. 101. © Microsoft Corporation Machine learning and AI portfolio What engines do you want to use? Deployment target Which experience do you want? Build your own or consume pre-trained models? Microsoft ML & AI products Build your own Azure Machine Learning Code first (On-prem) ML Server On-prem Hadoop SQL Server (cloud) BYOT SQL Server Hadoop Azure Batch DSVM Spark Visual tooling (cloud) AML Studio Consume Cognitive services, bots Spark ML, SparkR, SparklyR Notebooks Jobs Azure Databricks Spark When to use what
  102. 102. A D V A N C E D A N A L Y T I C S O N B I G D A T A INGEST STORE PREP & TRAIN MODEL & SERVE Cosmos DB Business/custom apps (structured) Files (unstructured) Media (unstructured) Logs (unstructured) Azure Data Lake Store Gen2Azure Data Factory Azure SQL Data Warehouse Azure Analysis Services Power BI PolyBase SparkR Azure Databricks Microsoft Azure also supports other Big Data services like Azure HDInsight, Azure Machine Learning to allow customers to tailor the above architecture to meet their unique needs. Real-time apps
  103. 103. Artificial Intelligence Decision Tree Big Data Decision Tree v4 Business Intelligence Solutions Decision Tree
  104. 104. Q & A ? James Serra, Big Data Evangelist Email me at: Follow me at: @JamesSerra Link to me at: Visit my blog at: (where this slide deck is posted via the “Presentations” link on the top menu)
  105. 105. Customer analytics Financial modeling Risk, fraud, threat detection Credit analytics Marketing analytics Faster innovation for a better customer experience Improved consumer outcomes and increased revenue Enhanced customer experience with machine learning Transform growth with predictive analytics Improved customer engagement with machine learning Customer profiles Credit history Transactional data LTV Loyalty Customer segmentation CRM data Credit data Market data CRM Credit Risk Merchant records Products and services Clickstream data Products Services Customer service data Customer 360 degree evaluation Customer segmentation Reduced customer churn Underwriting, servicing and delinquency handling Insights for new products Commercial/retail banking, securities, trading and investment models Decision science, simulations and forecasting Investment recommendations Real-time anomaly detection Card monitoring and fraud detection Security threat identification Risk aggregation Enterprise DataHub Regulatory and compliance analysis Credit risk management Automated credit analytics Recommendation engine Predictive analytics and targeted advertising Fast marketing and multi- channel engagement Customer sentiment analysis Transaction data Demographics Purchasing history Trends Effective customer engagement Decision services management Risk and revenue management Risk and compliance management Recommendation engine
  106. 106. Genomics and precision medicine Clinical and claims data GPU image processing IoT device analytics Social analytics Faster innovation for drug development Improved outcomes and increased revenue Diagnostics leveraging machine learning Predictive analytics transforms quality of care Improved patient communications and feedback FAST-Q BAM SAM VCF Expression HL7/CCD 837 Pharmacy Registry EMR Readings Time series Event data Social media Adverse events Unstructured Single cell sequencing Biomarker, genetic, variant and population analytics ADAM and HAIL on Databricks Claims data warehouse Readmission predictions Efficacy and comparative analytics Prescription adherence Market access analysis Graphic intensive workloads Deep learning using Tensor Flow Pattern recognition Aggregation of streaming events Predictive maintenance Anomaly detection Real-time patient feedback via topic modelling Analytics across publication data MRI X-RAY CT Ultrasound DNA sequences Real world analytics Image deep learning Sensor data Social data listening
  107. 107. Content personalization Customer churn prevention Recommendation engine Predictive analytics Sentiment analysis Faster innovation for customer experience Improved consumer outcomes and increased revenue Enhance user experience with machine learning Predictive analytics transforms growth Improved consumer engagement with machine learning Customer profiles Viewing history Online activity Content sources Channels Customer profiles Online activity Content distribution Services data Transactions Subscriptions Demographics Credit data Content metadata Ratings Comments Social media activity Personalized viewing and engagement experience Click-path optimization Next best content analysis Improved real time ad targeting Quality of service and operational efficiency Market basket analysis Customer behavior analysis Click-through analysis Ad effectiveness Content monetization Fraud detection Information-as-a-service High value user engagement Predict audience interests Network performance and optimization Pricing predictions Nielsen ratings and projections Mobile spatial analytics Demand-elasticity Social network analysis Promotion events time-series analysis Multi-channel marketing attribution Consumption logs Clickstream and devices Marketing campaign responses Personalized recommendations Effective customer retention Information optimization Inventory allocation Consumer engagement analysis
  108. 108. Next best and personalized offers Store design and ergonomics Data-driven stock, inventory, ordering Assortment optimization Real-time pricing optimization Faster innovation for customer experience Improved consumer outcomes and increased revenue Omni-channel shopping experience with machine learning Predictive analytics transforms growth Improved consumer engagement with machine learning Customer profiles Shopping history Online activity Social network analysis Shopping history Online activity Floor plans App data Demographics Buyer perception Consumer research Market/competitive analysis Historical sales data Price scheduling Segment level price changes Customer 360/consumer personalization Right product, promotion, at right time Multi-channel promotion Path to purchase In-store experience Workforce and manpower optimization Predict inventory positions and distribution Fraud detection Market basket analysis Economic modelling Optimization for foot traffic, Online interactions Flat and declining categories Demand-elasticity Personal pricing schemes Promotion events Multi-channel engagement Demand plans Forecasts Sales history Trends Local events/weather patterns Recommendation engine Effective customer engagement Inventory optimization Inventory allocation Consumer engagement
  109. 109. Customer value analytics Next best and personalized offers Risk and fraud management Sales and campaign optimization Sentiment analysis Faster innovation for customer growth Improved outcomes and increased revenue Risk management with machine learning Predictive analytics transforms growth Improved customer engagement with machine learning Customer profiles Online history Transaction data Loyalty Customer segmentation CRM data Credit data Market data CRM Merchant records Products Services Marketing data Social media Online history Customer service data Customer 360, segmentation aggregation and attribution Audience modelling/index report Reduce customer churn Insights for new products Historical bid opportunity as a service Right product, promotion, at right time Real time ad bidding platform Personalized ad targeting Ad performance reporting Real-time anomaly detection Fraud prevention Customer spend and risk analysis Data relationship maps Optimizing return on ad spend and ad placement Multi-channel promotion Ideal customer traits Optimized ad placement Opinion mining/social media analysis Deeper customer insights Customer loyalty programs Shopping cart analysis Transaction data Demographics Purchasing history Trends Effective customer engagement Recommendation engine Risk and fraud analysis Campaign reporting analytics Brand promotion and customer experience
  110. 110. Digital oil field/ oil production Industrial IoT Supply-chain optimization Safety and security Sales and marketing analytics Faster innovation for revenue growth Improved outcomes and increased revenue Optimizing supply- chain with machine learning Predictive analytics transforms safety and security Improved customer engagement with machine learning Field data Asset data Demographics Production data Sensor stream data UAVs images Inventory data Production data Sensor stream data Transport Retail data Grid production data Refinery tuning parameters Clickstream data Products Services Market data Competitive data Demographics Production optimization Integrate exploration and seismic data Minimize lease operating expenses Decline curve analysis Pipeline monitoring Preventive maintenance Smart grids and microgrids Grid operations, field service Asset performance as a service Trade monitoring, optimization Retail mobile applications Vendor management - construction, transportation, truck and delivery optimization Real-time anomaly detection Predictive analytics Industrial safety Environment health and safety Fast marketing and multi-channel engagement Develop new products and monitor acceptance of rates Predictive energy trading Deep customer insights Transaction data Demographics Purchasing history Trends Upstream optimization, maximize well life Grid operations, asset inventory optimization Supply-chain optimization Risk optimization Recommendations engine
  111. 111. Intrusion detection and predictive analytics Security intelligence Fraud detection and prevention Security compliance reporting Fine-grained data analytics security Prevent complex threats with machine learning Faster innovation for threat prevention Risk management with machine learning Transform security with improved visibility Limit malicious insiders to transform growth Firewall/network logs Apps Data access layers Firewall/network logs Network flows Authentications Firewall/network logs Web Applications Devices OS Files Tables Clusters Reports Dashboards Notebooks Prevention of DDoS attacks Threat classifications Data loss/anomaly detection in streaming Cybermetrics and changing use patterns Real-time data correlation Anomaly detection Security context, enrichment Offence scoring, prioritization Security orchestration e-Tailing Inventory monitoring Social media monitoring Phishing scams Piracy protection Ad-hoc/historic incident reports SOC/NOC dashboards Deep OS auditing Data loss detection in IoT User behavior analytics Role-based access controls Auditing and governance File integrity monitoring Row level and column level access permissions Firewall/network logs Web/app logs Social media content Security controls to leverage all data Actionable threat intelligence Risk and fraud analysis Compliance management Identity and access management for analytics