[第35回 Machine Learning 15minutes!] Microsoft AI Updates
•
1 like•704 views
第35回 Machine Learning 15minutes! (2019/04/27) https://machine-learning15minutes.connpass.com/event/124780/ [第35回 Machine Learning 15minutes!] Microsoft AI Updates https://satonaoki.wordpress.com/2019/04/27/ml15min-microsoft-ai-2/
Recommended
Recommended
More Related Content
What's hot
What's hot (20)
Similar to [第35回 Machine Learning 15minutes!] Microsoft AI Updates
Similar to [第35回 Machine Learning 15minutes!] Microsoft AI Updates (20)
More from Naoki (Neo) SATO
More from Naoki (Neo) SATO (20)
Recently uploaded
Recently uploaded (20)
[第35回 Machine Learning 15minutes!] Microsoft AI Updates
- 1. SATO Naoki (Neo) - @satonaoki Microsoft Confidential
- 3. Data AI
- 4. Data AI Data modernization to Azure Globally distributed data Cloud Scale Analytics Data Modernization on-premises AI apps & agents Knowledge mining
- 5. Domain specific pretrained models To simplify solution development Azure Databricks Machine Learning VMs Popular frameworks To build advanced deep learning solutions TensorFlowPyTorch ONNX Azure Machine Learning LanguageSpeech … SearchVision Productive services To empower data science and development teams Powerful infrastructure To accelerate deep learning Scikit-Learn Azure Notebooks Jupyter Familiar Data Science tools To simplify model development Visual Studio Code Command line CPU GPU FPGA From the Intelligent Cloud to the Intelligent Edge
- 6. Infuse apps with powerful, pre-trained AI models Customize easily and tailor to your needs Vision Speech Language Bing Search … Computer Vision | Video Indexer | Face | Content Moderator Speech to Text | Text to Speech | Speech Translation | Speaker Recognition Text Analytics | Spell Check | Language Understanding | Text Translation | QnA Maker Big Web Search | Video Search | Image Search | Visual Search | Entity Search | News Search | Autosuggest
- 12. Domain specific pretrained models To simplify solution development Azure Databricks Machine Learning VMs Popular frameworks To build advanced deep learning solutions TensorFlowPyTorch ONNX Azure Machine Learning LanguageSpeech … SearchVision Productive services To empower data science and development teams Powerful infrastructure To accelerate deep learning Scikit-Learn Familiar Data Science tools To simplify model development CPU GPU FPGA From the Intelligent Cloud to the Intelligent Edge Azure Notebooks JupyterVisual Studio Code Command line
- 13. Choose any python development environment And improve data science productivity PyCharmAzure NotebooksVisual Studio Code Command lineZeppelin Interactive widgets for Jupyter Notebooks Azure Machine Learning for Visual Studio Code extension Jupyter Get started with AML on Azure Notebooks: http://aka.ms/aznotebooks-aml
- 14. Domain specific pretrained models To simplify solution development Popular frameworks To build advanced deep learning solutions Productive services To empower data science and development teams Powerful infrastructure To accelerate deep learning Familiar Data Science tools To simplify model development From the Intelligent Cloud to the Intelligent Edge Azure Databricks Machine Learning VMs TensorFlowPyTorch ONNX Azure Machine Learning LanguageSpeech … SearchVision Scikit-Learn Azure Notebooks JupyterVisual Studio Code Command line CPU GPU FPGA
- 15. Build advanced deep learning solutions Use your favorite deep learning frameworks without getting locked into one framework ONNX Community project created by Facebook and Microsoft Use the best tool for the job. Train in one framework and transfer to another for inference TensorFlow PyTorch Scikit-Learn MXNet Chainer Keras
- 18. Frameworks Azure Create Deploy Services Devices Azure Machine Learning services Ubuntu VM Windows Server 2019 VM Azure Custom Vision Service ONNX Model Windows devices Other devices (iOS, etc.)
- 20. Domain specific pretrained models To simplify solution development Popular frameworks To build advanced deep learning solutions Productive services To empower data science and development teams Powerful infrastructure To accelerate deep learning Familiar Data Science tools To simplify model development From the Intelligent Cloud to the Intelligent Edge Azure Databricks Machine Learning VMs TensorFlowPyTorch ONNX Azure Machine Learning LanguageSpeech … SearchVision Scikit-Learn Azure Notebooks JupyterVisual Studio Code Command line CPU GPU FPGA
- 21. + To empower data science and development teams Develop models faster with automated machine learning Use any Python environment and ML frameworks Manage models across the cloud and the edge. Prepare data clean data at massive scale Enable collaboration between data scientists and data engineers Access machine learning optimized clusters Azure Machine Learning Python-based machine learning service Azure Databricks Apache Spark-based big-data service
- 22. Bring AI to everyone with an end-to-end, scalable, trusted platform Built with your needs in mind Support for open source frameworks Managed compute DevOps for machine learning Simple deployment Tool agnostic Python SDK Automated machine learning Seamlessly integrated with the Azure Portfolio Boost your data science productivity Increase your rate of experimentation Deploy and manage your models everywhere
- 24. Fast, easy, and collaborative Apache Spark™-based analytics platform Built with your needs in mind Optimized Apache Spark environmnet Collaborative workspace Integration with Azure data services Autoscale and autoterminate Optimized for distributed processing Support for multiple languages and libraries Seamlessly integrated with the Azure Portfolio Increase productivity Build on a secure, trusted cloud Scale without limits
- 26. Leverage your favorite deep learning frameworks AZURE ML SERVICE Increase your rate of experimentation Bring AI to the edge Deploy and manage your models everywhere TensorFlow MS Cognitive Toolkit PyTorch Scikit-Learn ONNX Caffe2 MXNet Chainer AZURE DATABRICKS Accelerate processing with the fastest Apache Spark engine Integrate natively with Azure services Access enterprise-grade Azure security
- 27. What to use when? + 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, Pandas, NumPy etc.) Azure Databricks + Azure ML service (Spark MLib and OSS frameworks + Automated ML, Model Registry)
- 28. Domain specific pretrained models To simplify solution development Popular frameworks To build advanced deep learning solutions Productive services To empower data science and development teams Powerful infrastructure To accelerate deep learning Familiar Data Science tools To simplify model development From the Intelligent Cloud to the Intelligent Edge Azure Databricks Machine Learning VMs TensorFlowPyTorch ONNX Azure Machine Learning LanguageSpeech … SearchVision Scikit-Learn Azure Notebooks JupyterVisual Studio Code Command line CPU GPU FPGA
- 29. Accelerate deep learning General purpose machine learning D, F, L, M, H Series CPUs Optimized for flexibility Optimized for performance GPUs FPGAs Deep learning N Series Specialized hardware accelerated deep learning AML hardware accelerated models (Project Brainwave)
- 30. Simplify deployment + accelerate inferencing with ONNX runtime Track models in production Capture model telemetry From the Intelligent Cloud to the Intelligent Edge On-premisesCloud
- 32. Automated machine learning Machine learning DevOps Machine Learning 95 % Accelerated model building Azure DevOps integration for CI/CD
- 33. Automated machine learning Machine learning DevOps Machine Learning 95 % Accelerated model building Azure DevOps integration for CI/CD
- 34. How much is this car worth? Azure Machine Learning Automated machine learning
- 35. Model creation is typically a time consuming process Mileage Condition Car brand Year of make Regulations … Parameter 1 Parameter 2 Parameter 3 Parameter 4 … Gradient Boosted Nearest Neighbors SGD Bayesian Regression LGBM … Mileage Gradient Boosted Criterion Loss Min Samples Split Min Samples Leaf XYZ Model Which algorithm? Which parameters?Which features? Car brand Year of make
- 36. Which algorithm? Which parameters?Which features? Mileage Condition Car brand Year of make Regulations … Gradient Boosted Nearest Neighbors SGD Bayesian Regression LGBM … Nearest Neighbors Criterion Loss Min Samples Split Min Samples Leaf XYZ Model Iterate Gradient Boosted N Neighbors Weights Metric P ZYX Mileage Car brand Year of make Model creation is typically a time consuming process Car brand Year of make Condition
- 37. Which algorithm? Which parameters?Which features? Iterate Model creation is typically a time consuming process
- 38. Enter data Define goals Apply constraints Azure Machine Learning accelerates model development with automated machine learning Input Intelligently test multiple models in parallel Optimized model
- 39. 70%95% Azure Machine Learning accelerates model selection with model explainability Feature importance Mileage Condition Car brand Year of make Regulations Model B (70%) Mileage Condition Car brand Year of make Regulations Feature importance Model A (95%)
- 40. Automated machine learning Machine learning DevOps Machine Learning 95 % Accelerated model building Azure DevOps integration for CI/CD
- 41. ServeStore Prep and trainIngest Batch data Streaming data Azure Kubernetes service Power BI Azure analysis services Azure SQL data warehouse Cosmos DB, SQL DB Azure Data Lake Storage Azure Data Factory Azure Event Hubs Azure Databricks Azure Machine Learning service Apps Model Serving Ad-hoc Analysis Operational Databases
- 42. Register and Manage Model Build Image Build model (your favorite IDE) Deploy Service Monitor Model Train & Test Model Integrated with Azure DevOps
- 43. Prepare Data Register and Manage Model Train & Test Model Build Image … Build model (your favorite IDE) Deploy Service Monitor Model Prepare Experiment Deploy DevOps loop for data science
- 44. DevOps loop for data science Prepare Data Prepare Register and Manage Model Build Image … Build model (your favorite IDE) Deploy Service Monitor Model Train & Test Model
- 45. Model management in Azure Machine Learning Create/retrain model Create scoring files and dependencies Create and register image Monitor Register model Cloud Light Edge Heavy Edge Deploy image
- 46. Use leaderboards, side by side run comparison and model selection Conduct a hyperparameter search on traditional ML or DNN Leverage service-side capture of run metrics, output logs and models Manage training jobs locally, scaled-up or scaled-out Experimentation 95 % 80% 75% 90% 85%
- 47. Azure Databricks Remote support for other IDEs outside of native notebooks MLFlow for better DevOps with Azure Databricks and other ML pipelines Azure Machine Learning Python SDK support for popular IDEs & notebooks, including Azure Databricks Azure Machine Learning managed compute capabilities Introduce new models for FPGA scoring Robust ONNX support - runtime engine in AML, model operationalization in SQL Server Automated machine learning Deploy and manage models to IoT edge Extend Machine Learning services to SQL DB
- 50. Microsoft AI Lab https://www.ailab.microsoft.com/
- 51. AI for Good Idea Challenge https://www.ailab.microsoft.com/challenge