5. www.Suhail.Cloud #SuhailCloud @SuhailCloud
Machine Learning
• Machine learning is a subset of Artificial Intelligence (AI)
• Provides systems the ability to automatically learn and improve
from experience without being explicitly programmed.
• Process
• Prepare Data
• Build Model (Acquire Knowledge)
• Use Model (Predict Decisions)
• Results are probabilistic
10. www.Suhail.Cloud #SuhailCloud @SuhailCloud
Reuse .Net Skills
C# and F# for custom models
Proven at scale
Azure, Windows, Office
Used in PowerBI, Outlook, Visual Studio…
Extensible
Tenserflow, ONNX and Infer.Net
Custom LM made easy
Automated ML and Tools (Model builder and CLI)
16. www.Suhail.Cloud #SuhailCloud @SuhailCloud
Automated Machine Learning – AutoML (Preview state)
Automate the creation of the model
• You don't need to write the code by yourself to train a model
• You simply need to provide your datasets.
• The "best" model and the code for running it will be generated for
you.
Currently only support Binary-Classification, Multiclass
Classification and Regression.
In upcoming versions will be supporting additional ML Tasks such
as Recommendations, Anomaly Detection, Clustering, etc..
18. www.Suhail.Cloud #SuhailCloud @SuhailCloud
ML.Net Model Builder (Preview)
• UI tooling in Visual Studio as Visual studio extension
• Uses Automated Machine Learning (AutoML) to easily allow to
build, train and ship custom machine learning models
• Developers with no ML expertise can use this tool easily
• Model Builder currently supports Regression, Binary-Classification
and Multi-Classification tasks.
19. www.Suhail.Cloud #SuhailCloud @SuhailCloud
• Currently support .tsv, .csv, .txt, and SQL as the data types
• If you have a .txt file, columns should be separated with ',' or ';' or
'/t‘
• The files must have a header row.
21. www.Suhail.Cloud #SuhailCloud @SuhailCloud
ML.Net CLI (Preview state)
The ML.NET CLI is a tool you can run on any command-prompt
• Windows – Poweshell and CMD
• Mac or Linux – Bash
Generates good quality ML.NET models based on training datasets
you provide.
It also generates sample C# code to run/score the model
Generates C# code that was used to create/train it so you can
research what algorithm and settings it is using.