Step into Machine Learning .NET
summary
Demos show concrete results not promises: a simple image classifier trains in about one minute with ML.NET Model Builder and predicts a held‑out circle at ~99% while a whiteboard demo fails without internet; a 100‑image bathroom dataset (≈50 with toilet, 50 without) produces a working binary classifier; object detection exports to ONNX/TensorFlow and runs YOLO to draw bounding boxes; a local tiny LLM (Pi 3, ~2 GB) runs in .NET but returns incorrect math and needs parameter tuning so it is usable but imperfect.
AI-written summary · about
chapters (14)
- 0:00Introduction
- 1:03Machine learning basics
- 3:50Local AI vs cloud
- 6:25ML.NET workflow
- 10:50Demo: Setting up ML.NET in Visual Studio
- 12:36Image classification demo
- 18:26Custom Vision AI demo
- 20:15Exporting models
- 21:19TensorFlow in ML.NET
- 24:37Toilet detection use case
- 27:32Handwriting recognition use case
- 28:44YOLO demo
- 33:34LLMs with ML.NET and Phi-3
- 39:08Q&A
related talks
59mMachine Learning in .NET (ML.NET)
58mExploring Machine Learning for .Net Developers
45mML: ML.NET: deep dive into dev AI
01h 03mMachine learning for C# developers: Introducing ML
59mBeyond Sentiment Analysis: Object Detection with ML NET
44mAutomated Machine Learning with ML.NET
01h 04mIntroduction to ML.NET
59mMachine Learning simplified for Developers with ML.NET