Se ha denunciado esta presentación.
Se está descargando tu SlideShare. ×

201909 Automated ML for Developers

Anuncio
Anuncio
Anuncio
Anuncio
Anuncio
Anuncio
Anuncio
Anuncio
Anuncio
Anuncio
Anuncio
Anuncio
Cargando en…3
×

Eche un vistazo a continuación

1 de 44 Anuncio

201909 Automated ML for Developers

Descargar para leer sin conexión

Microsoft has released Automated ML technologies for developers through ML.NET, Azure ML Service, and Azure Databricks. This presenter is a data scientist and Microsoft architect, and will give a comprehensive overview of the utility and use case of this automated technology for production solutions. The presentation includes code you can try now.

Microsoft has released Automated ML technologies for developers through ML.NET, Azure ML Service, and Azure Databricks. This presenter is a data scientist and Microsoft architect, and will give a comprehensive overview of the utility and use case of this automated technology for production solutions. The presentation includes code you can try now.

Anuncio
Anuncio

Más Contenido Relacionado

Presentaciones para usted (20)

Similares a 201909 Automated ML for Developers (20)

Anuncio

Más de Mark Tabladillo (20)

Más reciente (20)

Anuncio

201909 Automated ML for Developers

  1. 1. Data and AI Scientist @ Microsoft Cloud Solution Architect US CTO Customer Success @marktabnet
  2. 2. ML.NET Open Source Momentum 150K+ 1,427 1,528 106
  3. 3. ML.NET Customers Andy Gray, Executive Partner Evolution Software Design, Inc.
  4. 4. DESKTOP CLOUDWEB MOBILE ML .NET Your platform for building anything IoTGAMING
  5. 5. “It has exquisite buttons … with long sleeves …works for casual as well as business settings”{f(x) {f(x) Machine Learning “Programming the UnProgrammable”
  6. 6. f(x) Model Machine Learning creates a using this data Machine Learning “Programming the UnProgrammable”
  7. 7. ML.NET 1.0 Machine Learning framework for building custom ML Models Custom ML made easy Automated ML and Tools (Model Builder and CLI) Proven at scale Azure, Office, Windows Extensible TensorFlow, ONNX and Infer.NET Cross-platform and open-source Runs everywhere
  8. 8. 1. Data Example Comment Text Sentiment Wow... Loved this place. 1 Crust is not good. 0 Not tasty and the texture was just nasty. 0 The selection on the menu was great. 1
  9. 9. Text Featurizer Featurized Text [0.76, 0.65, 0.44, …] [0.98, 0.43, 0.54, …] [0.35, 0.73, 0.46, …] [0.39, 0, 0.75, …] Example Text Wow... Loved this place. Crust is not good. Not tasty and the texture was just nasty. The selection on the menu was great. 2. Transformers
  10. 10. Example Estimator Comment Sentiment Wow... Loved this place. 1 Crust is not good. 0 Not tasty and the texture was just nasty. 0 The selection on the menu was great. 0 3. Estimators
  11. 11. Comment Text Sentiment Wow... Loved this place. 1 Crust is not good. 0 Not tasty and the texture was just nasty. 0 The selection on the menu was great. 1 Yelp review dataset Features (input) Label (output) Sentiment Analysis Is this a positive comment? Yes or no
  12. 12. Building blocks for a Data Science Project Data sources
  13. 13. What is automated machine learning? © Microsoft Corporation Automated machine learning (automated ML) automates feature engineering, algorithm and hyperparameter selection to find the best model for your data.
  14. 14. Automated ML Mission Democratize AI Scale AIAccelerate AI © Microsoft Corporation Azure Enable automated building of machine learning with the goal of accelerating, democratizing and scaling AI Enable Domain Experts & Developers to get rapidly build AI solutions Improve Productivity for Data Scientists, Citizen Data Scientists, App Developers & Analysts Build AI solutions at scale in an automated fashion
  15. 15. How much is this car worth? Machine Learning Problem Example
  16. 16. Model Creation Is Typically Time-Consuming Mileage Condition Car brand Year of make Regulations … Parameter 1 Parameter 2 Parameter 3 Parameter 4 … Gradient Boosted Nearest Neighbors SVM Bayesian Regression LGBM … Mileage Gradient Boosted Criterion Loss Min Samples Split Min Samples Leaf Others Model Which algorithm? Which parameters?Which features? Car brand Year of make
  17. 17. Criterion Loss Min Samples Split Min Samples Leaf Others N Neighbors Weights Metric P Others Which algorithm? Which parameters?Which features? Mileage Condition Car brand Year of make Regulations … Gradient Boosted Nearest Neighbors SVM Bayesian Regression LGBM … Nearest Neighbors Model Iterate Gradient BoostedMileage Car brand Year of make Car brand Year of make Condition Model Creation Is Typically Time-Consuming
  18. 18. Which algorithm? Which parameters?Which features? Iterate Model Creation Is Typically Time-Consuming
  19. 19. Enter data Define goals Apply constraints Output Automated ML Accelerates Model Development Input Intelligently test multiple models in parallel Optimized model
  20. 20. Automated ML Capabilities • Based on Microsoft Research • Brain trained with several million experiments • Collaborative filtering and Bayesian optimization • Privacy preserving: No need to “see” the data
  21. 21. Automated ML Capabilities • ML Scenarios: Classification & Regression, Forecasting • Languages: Python SDK for deployment and hosting for inference – Jupyter notebooks • Training Compute: Local Machine, AML Compute, Data Science Virtual Machine (DSVM), Azure Databricks* • Transparency: View run history, model metrics, explainability* • Scale: Faster model training using multiple cores and parallel experiments * In Preview
  22. 22. Data Preprocessing Feature Engineering Algorithm Selection Hyper-parameter Tuning Model Recommendation Interpretability & Explaining 1. 2. 3. 4. 5. 6. © Microsoft Corporation Azure Automated ML
  23. 23. Guardrails Class imbalance Train-Test split, CV, rolling CV Missing value imputation Detect high cardinality features Detect leaky features Detect overfitting Model Interpretability / Feature Importance
  24. 24. What’s new?
  25. 25. Latest announcements @ MS Build (Blog post with all the announcements) Automated ML in ML.NET Model Builder (Preview) • Train ML models from Visual Studio • Inference from your application © Microsoft Corporation Azure ML.NET Model Builder
  26. 26. ML.NET AutoML
  27. 27. Automated Machine Learning (AutoML)
  28. 28. On the command line, with the ML.NET CLI mlnet auto-train --task binary-classification --dataset "yelp_labelled.txt" --label-column-index 1 --has-header false --max-exploration-time 10
  29. 29. With a graphical user interface, with the the ML.NET Model Builder
  30. 30. https://github.com/dotnet/machinelearning- samples/tree/master/samples/csharp/getting- started/BinaryClassification_AutoML Via an application, with the automated ML API
  31. 31. Automated ML Customer Testimonials • Press-coverage from public preview: • CNET • VentureBeat • PRNewswire “I quite like your AutoML function. It gives me good results compared to other libraries I tested before (tpot and auto-sklearn) that I believe was only looking at scores and often gave me models that over-trained my data. And of course the model from your suggested code is better.” - Big oil company “I will start with AutoML and use the algorithm that AutoML recommends to further tune the model” - Data Scientist “I actually enjoy being able to use AutoML in a Jupyter notebook. The DataRobot interface was nice for non-experts, but for someone like me, it felt a bit basic.” - Data Scientist
  32. 32. https://dotnet.microsoft.com/apps/data/spark
  33. 33. https://dotnet.microsoft.com/learn/dotnet/architecture-guides
  34. 34. Gitter https://gitter.im/dotnet/mlnet
  35. 35. http://dot.net/ml http://aka.ms/mlnetsamples http://aka.ms/mlnetdocs http://aka.ms/mlnet

×