Developer Accessible Machine Learning

on YouTube ↗43m

" summary

Builds a linear regression on the UCI wine CSV using just one feature (alcohol), implements prediction and cost (MSE) in F sharp with an interactive REPL and F sharp type provider, splits 1,000/600 for training/test, minimizes cost with gradient descent (learning rate alpha, fixed steps), and visualizes stepwise convergence and predicted vs actual. Then recreates the pipeline in sure ML Studio drag‑and‑drop, inspects MAE/RMSE/R², exposes the model as a web service, and mentions libraries like CNTK, diff sharp and ml dotnet.

AI-written summary · about

" chapters (10)

1. 0:00Introduction
2. 7:00Linear Regression
3. 11:05Interactive Mode
4. 17:30Overfitting
5. 22:20Gradient Descent
6. 25:27Coding
7. 30:05Value
8. 31:16ML Studio
9. 39:40Results
10. 39:54Conclusion

" related talks

• 27mUsing C# for Data Science and Machine LearningJonathan Wood · Global Azure Virtual 2020
• 45mMachine Learning for .NET developersOlia Gavrysh · NDC London 2020
• 01h 02mMachine Learning with F#, ReduxMathias Brandewinder · NDC Sydney 2017
• 24mAzure ML, Azure Kubernetes Service, Model deploymentAmbarish Ganguly · Global Azure Virtual 2021
• 56mMachine Learning for .NET developersOlia Gavrysh · NDC Oslo 2020
• 59mA developers guide to Machine LearningTess Ferrandez-Norlander · NDC Oslo 2018
• 58mExploring Machine Learning for .Net DevelopersNiloshima Srivastava · AzConf 2020
• 01h 03mMachine learning for C# developers: Introducing MLJeff Prosise · DotNext 2019 Moscow