2018 08 01 C# Mexico Introduction to Machine Learning.Net
0 likes201 views
The document discusses ML.NET, a machine learning framework from Microsoft. Some key points: - ML.NET can be used to build custom machine learning models and uses pre-built models like TensorFlow. - It is open source, cross-platform (runs on Windows, Linux and macOS), and has been proven at scale within Microsoft products like Windows 10, PowerPoint and Excel. - ML.NET uses pipelines to load and prepare data, extract features, train models, evaluate models and deploy models for consumption.
2018 08 01 C# Mexico Introduction to Machine Learning.Net
- 1. Bruno Capuano Innovation Lead @Avanade @elbruno | http://elbruno.com
- 2. DESKTOP CLOUDWEB MOBILE ML .NET Your platform for building anything IoTGAMING
- 3. “It has exquisite buttons … with long sleeves …works for casual as well as business settings”{f(x) {f(x)
- 4. f(x) Model Machine Learning creates a Using this data
- 5. Is this A or B? How much? How many? How is this organized? Regression ClusteringClassification
- 6. MakeMagicHappen(); https://www.microsoft.com/net/learn/apps/machine -learning-and-ai
- 8. ML.NET is for building custom models Custom models Easier / Less Control Harder / Full Control Pre-built models TensorFlow ML.NETVisionSpeech LanguageKnowledge Search
- 9. Easy / Less Control Full Control / Harder Vision Speech Language Knowledge SearchLabs TextAnalyticsAPI client = new TextAnalyticsAPI(); client.AzureRegion = AzureRegions.Westus; client.SubscriptionKey = "1bf33391DeadFish"; client.Sentiment( new MultiLanguageBatchInput( new List<MultiLanguageInput>() { new MultiLanguageInput("en","0", "This vacuum cleaner sucks so much dirt") })); e.g. Sentiment Analysis using Azure Cognitive Services 9% positive Pre-built ML Models (Azure Cognitive Services)
- 10. Easy / Less Control Full Control / Harder Prepare Your Data Build & Train Run Build your own (custom) ML Models
- 11. Less Control / Easy Existing Solutions Build your own (custom) ML Models
- 12. 02 WHAT IS ML.NET? ML.NET is a framework first
- 13. ML.NET is a framework first
- 14. 03 WHAT IS ML.NET? ML.NET has been proven in large scale Microsoft products
- 15. ML.NET Usage at Microsoft + more! Windows 10 Power Point Excel Bing Ads
- 16. 04 WHAT IS ML.NET? ML.NET is Open Source & Cross-Platform
- 17. Microsoft Confidential Proven & Extensible Open Source https://github.com/dotnet/machinelearning Build your own Supported on Windows, Linux, and macOS Developer Focused ML.NET 0.4.0 (Preview) Machine Learning framework made for .NET developers
- 18. MakeMagicHappen(); https://www.microsoft.com/net/learn/apps/machine -learning-and-ai
- 21. Load Data Extract Features Train Model Evaluate Model Model consumption labels + plain text labels + feature vectors model
- 22. Load Data Extract Features Train Model Evaluate Model Model consumption labels + plain text labels + feature vectors Enter... in ML.NETLearningPipelines! model
- 23. Load Data Extract Features Train Model Evaluate Model Model consumption
- 24. MakeMagicHappen(); https://www.microsoft.com/net/learn/apps/machine -learning-and-ai
- 27. Bruno Capuano Innovation Lead @Avanade @elbruno | http://elbruno.com