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.

Automated machine learning - Global AI night 2019

48 views

Published on

At global AI night in Verona i talk about automated-ml and about the machine learning service world on azure.

Published in: Data & Analytics
  • Be the first to comment

  • Be the first to like this

Automated machine learning - Global AI night 2019

  1. 1. 1 ARGOMENTO Global AI Night 2019 Intermediate Track - Automated machine learning
  2. 2. Automated Machine Learning @marco_zamana MarcoZama marco-zamana Marco Zamana
  3. 3. Automated Machine Learning Data scientist and developers "magic" machine learning solution
  4. 4. Automated Machine Learning Machine learning lifecycle 1. Business Understanding 2. Data Acquisition 3. Modeling 4. Operationalization Every Machine Learning solution should start with the business problem you are working to solve followed by acquiring and exploring the data that is needed.
  5. 5. Automated Machine Learning Source: scikit-learn machine learning library Decisions • What ml algorithm would be best? • What parameter values should they use for the chosen classifier? And many more… machine learning pipeline
  6. 6. 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 Automated Machine Learning Model Creation Is Typically Time-Consuming
  7. 7. 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 Automated Machine Learning Model Creation Is Typically Time-Consuming
  8. 8. Which algorithm? Which parameters?Which features? Iterate Automated Machine Learning Model Creation Is Typically Time-Consuming
  9. 9. Automated Machine Learning The combination of data pre-processing steps, learning algorithms, and hyperparameter settings that go into each machine learning solution. Machine learning pipeline ACCURACY
  10. 10. Automated Machine Learning Simplifying machine learning What if a developer or data scientist could access an automated service that identifies the best machine learning pipelines for their labelled data?
  11. 11. Automated Machine Learning Automated ML empowers customers, with or without data science expertise, to identify an end-to-end machine learning pipeline for any problem, achieving higher accuracy while spending far less of their time. And it enables a significantly larger number of experiments to be run, resulting in faster iteration towards production-ready intelligent experiences.
  12. 12. Enter data Define goals Apply constraints OutputInput Intelligently test multiple models in parallel Optimized model Automated Machine Learning Automated ML Accelerates Model Development
  13. 13. Automated Machine Learning Automated ML is based on a breakthrough from our Microsoft Research division. The approach combines ideas from collaborative filtering and Bayesian optimization to search an enormous space of possible machine learning pipelines intelligently and efficiently. It's essentially a recommender system for machine learning pipelines. Similar to how streaming services recommend movies for users…
  14. 14. Automated Machine Learning … Automated ML recommends machine learning pipelines for data sets.
  15. 15. Automated Machine Learning No need to “see” the data Automated ML accomplishes all this without having to see the customer’s data, preserving privacy. Automated ML is designed to not look at the customer’s data. Customer data and execution of the machine learning pipeline both live in the customer’s cloud subscription (or their local machine), which they have complete control of.
  16. 16. Automated Machine Learning No need to “see” the data We trained automated ML’s probabilistic model by running hundreds of millions of experiments, each involving evaluation of a pipeline on a data set. This training now allows the automated ML service to find good solutions quickly for your new problems. And the model continues to learn and improve as it runs on new ML problems – even though, as mentioned above, it does not see your data.
  17. 17. Automated Machine Learning Automated ML is available to try in the preview of Azure Machine Learning. Currently support classification and regression ML model recommendation on numeric and text data, with support for automatic feature generation (including missing values imputations, encoding, normalizations and heuristics-based features), feature transformations and selection. Data scientists can use automated ML through the Azure Machine Learning Python SDK and Jupyter notebook experience. Training can be performed on a local machine or by leveraging the scale and performance of Azure by running it on Azure Machine Learning managed compute. Customers have the flexibility to pick a pipeline from automated ML and customize it before deployment. Model explainability, ensemble models, full support for Azure Databricks and improvements to automated feature engineering will be coming soon. And NOW?
  18. 18. WorkShop
  19. 19. Automated Machine Learning Energy Demand Scenario This scenario focuses on energy demand forecasting where the goal is to predict the future load on an energy grid. It is a critical business operation for companies in the energy sector as operators need to maintain the fine balance between the energy consumed on a grid and the energy supplied to it.
  20. 20. @cloudgen_verona #GlobalAINight
  21. 21. Grazie Domande? MarcoZama @marco_zamana marco-zamana

×