Oct2018 Meetup: Get Started with Azure Machine Learning by Sebastiano Galazzo

Links:
https://docs.microsoft.com/en-us/windows/ai/
http://onnx.ai/
https://gallery.azure.ai/models
https://www.customvision.ai/
https://github.com/galazzo/Microsoft-CognitiveServices-CPP-SDK

Machine Learning has moved out of the lab and into production systems. Understanding how to work with this technology is one of the essential skills for developers today. In this session, you will learn the basics of machine learning, how to use existing models and services in your apps and how to get started with creating your own models.

Speaker: Sebastiano Galazzo
Sebastiano is an IT Manager at axélero, a Microsoft MVP and a conference speaker with over 15 years of experience in AI and machine learning.
He has dedicated the last few years to designing and developing algorithms to tackle the challenges of natural language processing, image recognition and predictive analysis through machine learning.

You can find him at:
https://www.linkedin.com/in/sebastianogalazzo/
https://twitter.com/galazzoseba

Transcript

1. Get Started with Machine Learning Sebastiano Galazzo twitter: @galazzoseba Microsoft MVP for Artificial Intelligence
2. why should I care about AI and ML? As a developer,
3. Some problems are difficult to solve using traditional algorithms and procedural programming.
4. AI solves hard problems Smart Ink​ • Classify strokes as text, shapes, freehand drawings​ • Classify text into words, paragraphs, lines, bullets​ • Extract entities: phone numbers, names, dates​ • Assign meanings: date references, known contacts
5. Prepare Data Build & Train Evaluate Azure Databricks Azure Machine Learning Quickly launch and scale Spark on demand Rich interactive workspace and notebooks Seamless integration with all Azure data services Broad frameworks and tools support: TensorFlow, Cognitive Toolkit, Caffe2, Keras, MxNET, PyTorch In the cloud – on the edge Docker containers Get started with machine learning Windows Machine Learning
6. Scalability Low latency Flexibility AI on the edge
7. Windows ML
8. 1. Developers can focus on their data and their scenarios, using Windows ML for model evaluation 2. Enables using ML models trained with a diverse set of toolkits 3. Hardware acceleration gets fast evaluation results across the diversity of the entire Windows device ecosystem. Windows ML solves three problems for you Direct3D GPU CPU DirectML Model Inference Engine WinML Win32 API WinML UWP API Win32 App WinML Runtime UWP App
9. Windows ML uses ONNX models
10. • Azure Machine Learning Services gives you an end-to-end solution to prepare data, and train your model in the Cloud. • WinMLTools converts existing models from CoreML, scikit-learn, LIBSVM, and XGBoost • Azure Custom Vision makes it easy to create your own image models - https://customvision.ai/ • Azure AI Gallery curates models for use with Windows ML - https://gallery.azure.ai/models How do I get ONNX models to use in my application?
11. Hello WinML! Demo
12. Azure Custom Vision Demo
13. Microsoft Cognitive Services C++ SDK https://github.com/galazzo/Microsoft-CognitiveServices-CPP-SDK
14. Thanks! Github: https://github.com/galazzo Twitter: @galazzoseba Email: sebastiano.galazzo@gmail.com Linkedin: https://it.linkedin.com/in/sebastianogalazzo