Advanced Machine Learning .NET Applications
41mAdvanced2023-11-30
Authors
Sam Nasr
Course details
Take your machine learning .NET applications to the next level in this course, with software engineer Sam Nasr. Join Sam as he explores using ML.Net with other frameworks like ONNX and TensorFlow. In addition, he discusses best practices for properly collecting data for ML, source control, versioning, and common pitfalls.
Skills covered
.NETMachine LearningAdvancedSoftware Development ToolsArtificial Intelligence (AI)MicrosoftSoftware Development
Concepts
0. Introduction
- 01 - Advanced machine learning .NET
- 02 - What you should know
1. Preparing Data for Machine Learning
- 03 - Collecting data correctly
- 04 - Utilize SME
- 05 - Data types and structure
- 06 - Business logic
- 07 - Outliers
- 08 - Biases
- 09 - Data cleansing tools
- 10 - Demo - Checking data
2. How to Generate an ONNX Model
- 11 - What is ONNX
- 12 - Set up the .NET project for ONNX
- 13 - Create a model
- 14 - Generate an ONNX model
- 15 - Using Netron
- 16 - Demo - Generate an ONNX model in Visual Studio
3. How to Utilize TensorFlow Framework
- 17 - Image recognition vs. categorization
- 18 - What is TensorFlow
- 19 - Set up the .NET project for TensorFlow
- 20 - Train the model
- 21 - Evaluate the model
- 22 - Demo - Train a TensorFlow model in Visual Studio
4. Model Maintenance
- 23 - What is MLOps
- 24 - Retraining the model
- 25 - Versioning
- 26 - Source control
5. Common Pitfalls
- 27 - Machine Learning Model not in the context menu
- 28 - Is 32-bit supported on Windows
- 29 - Ensure the app is targeting x64 or x86
- 30 - New project with a different build target
- 31 - Challenge - Training and comparing ML.NET models
- 32 - Solution - Training and comparing ML.NET models
Conclusion
- 33 - Next steps