Artificial Intelligence and
Machine Learning for .NET
developers
Oleksandr Krakovetskyi
DevRain
About
1. CEO DevRain
2. CTO DonorUA
3. Ph.D. in Computer Science
4. Microsoft Regional Director
5. Microsoft Artificial Intelligence
Most Valuable Professional
AI Tools
Visual Studio Tools for Artificial Intelligence
https://visualstudio.microsoft.com/downloads/ai-tools-vs/
Azure Machine Learning for Visual Studio Code
https://github.com/Microsoft/vscode-tools-for-ai
Azure Machine Learning Studio
https://studio.azureml.net/
Pre-built AI
Azure Cognitive Services
RESTful intelligent APIs for Vision, Speech, Language, Knowledge and Search
https://azure.microsoft.com/en-us/services/cognitive-services/
Azure Cognitive Services Labs
Early look at emerging Cognitive Services technologies
https://labs.cognitive.microsoft.com/
Custom AI
Azure Machine Learning Service
Accelerate the end-to-end machine learning lifecycle
https://azure.microsoft.com/en-us/services/machine-learning-service/
Azure Cognitive Services Custom Vision
Microsoft Cognitive Services Custom Vision
https://www.customvision.ai/
Conversational AI
LUIS
Fast and effective way of adding language understanding to applications
https://luis.ai
QnA Maker
Service to train AI to respond to user's questions in
a conversational way, https://qnamaker.ai
Conversational AI
Dispatch
Use multiple LUIS and QnA models
https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-tutorial-
dispatch?view=azure-bot-service-4.0&tabs=csharp
Microsoft Bot Framework
A framework for building enterprise-grade conversational
AI experiences, https://dev.botframework.com/
Demo
Machine Learning for .NET
ML.NET
An open source and cross-platform machine learning framework
https://dotnet.microsoft.com/apps/machinelearning-ai/ml-dotnet
Sentiment analysis, Product recommendation, Price prediction, Customer
segmentation, GitHub labeler, Fraud detection, Spam detection, Image
classification, Sales forecasting.
Machine Learning
Machine Learning
Movie Recommender
In the *.csv files, there
are four columns:
• userId (feature)
• movieId (feature)
• Rating (label)
• timestamp
Movie Recommender
Incredibles 2
(2018)
The Avengers
(2012)
Guardians of the
Galaxy (2014)
User 1 Watched and liked
movie
Watched and liked
movie
Watched and liked
movie
User 2 Watched and liked
movie
Watched and liked
movie
Has not watched –
RECOMMEND
Movie Recommender
1. The root of mean squared error (RMS or RMSE) is used to measure the
differences between the model predicted values and the test dataset observed
values. Technically it's the square root of the average of the squares of the
errors. The lower it is, the better the model is.
2. R Squared indicates how well data fits a model. Ranges from 0 to 1. A value of
0 means that the data is random or otherwise can't be fit to the model. A
value of 1 means that the model exactly matches the data. You want your R
Squared score to be as close to 1 as possible.
Demo
Not Hotdog
Data Science VMs
Comprehensive pre-configured
virtual machines for data science
modelling, development and
deployment.
https://azure.microsoft.com/en-
us/services/virtual-
machines/data-science-virtual-
machines/
Microsoft Research Open Data
A collection of free datasets from Microsoft Research
to advance state-of-the-art research in areas such as
natural language processing, computer vision, and
domain specific sciences. Download or copy directly
to a cloud-based Data Science Virtual Machine for a
seamless development experience.
https://msropendata.com/
AI School
Dive in and learn how to start building intelligence into your
solutions with the Microsoft AI platform, including pre-trained
AI services like Cognitive Services and Bot Framework, as well
as deep learning tools like Azure Machine Learning, Visual
Studio Code Tools for AI, and Cognitive Toolkit. Our platform
enables any developer to code in any language and infuse AI
into your apps. Whether your solutions are existing or new,
this is the intelligence platform to build on.
https://aischool.microsoft.com/en-us
Q&A
Oleksandr Krakovetskyi
alex.krakovetskiy@devrain.com
@sashaeve
fb.com/alex.krakovetskiy

2019 04-13 ai for .net developers (fwdays)

  • 1.
    Artificial Intelligence and MachineLearning for .NET developers Oleksandr Krakovetskyi DevRain
  • 2.
    About 1. CEO DevRain 2.CTO DonorUA 3. Ph.D. in Computer Science 4. Microsoft Regional Director 5. Microsoft Artificial Intelligence Most Valuable Professional
  • 4.
    AI Tools Visual StudioTools for Artificial Intelligence https://visualstudio.microsoft.com/downloads/ai-tools-vs/ Azure Machine Learning for Visual Studio Code https://github.com/Microsoft/vscode-tools-for-ai Azure Machine Learning Studio https://studio.azureml.net/
  • 5.
    Pre-built AI Azure CognitiveServices RESTful intelligent APIs for Vision, Speech, Language, Knowledge and Search https://azure.microsoft.com/en-us/services/cognitive-services/ Azure Cognitive Services Labs Early look at emerging Cognitive Services technologies https://labs.cognitive.microsoft.com/
  • 6.
    Custom AI Azure MachineLearning Service Accelerate the end-to-end machine learning lifecycle https://azure.microsoft.com/en-us/services/machine-learning-service/ Azure Cognitive Services Custom Vision Microsoft Cognitive Services Custom Vision https://www.customvision.ai/
  • 7.
    Conversational AI LUIS Fast andeffective way of adding language understanding to applications https://luis.ai QnA Maker Service to train AI to respond to user's questions in a conversational way, https://qnamaker.ai
  • 8.
    Conversational AI Dispatch Use multipleLUIS and QnA models https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-tutorial- dispatch?view=azure-bot-service-4.0&tabs=csharp Microsoft Bot Framework A framework for building enterprise-grade conversational AI experiences, https://dev.botframework.com/
  • 9.
  • 10.
    Machine Learning for.NET ML.NET An open source and cross-platform machine learning framework https://dotnet.microsoft.com/apps/machinelearning-ai/ml-dotnet Sentiment analysis, Product recommendation, Price prediction, Customer segmentation, GitHub labeler, Fraud detection, Spam detection, Image classification, Sales forecasting.
  • 11.
  • 12.
  • 13.
    Movie Recommender In the*.csv files, there are four columns: • userId (feature) • movieId (feature) • Rating (label) • timestamp
  • 14.
    Movie Recommender Incredibles 2 (2018) TheAvengers (2012) Guardians of the Galaxy (2014) User 1 Watched and liked movie Watched and liked movie Watched and liked movie User 2 Watched and liked movie Watched and liked movie Has not watched – RECOMMEND
  • 15.
    Movie Recommender 1. Theroot of mean squared error (RMS or RMSE) is used to measure the differences between the model predicted values and the test dataset observed values. Technically it's the square root of the average of the squares of the errors. The lower it is, the better the model is. 2. R Squared indicates how well data fits a model. Ranges from 0 to 1. A value of 0 means that the data is random or otherwise can't be fit to the model. A value of 1 means that the model exactly matches the data. You want your R Squared score to be as close to 1 as possible.
  • 16.
  • 17.
  • 18.
    Data Science VMs Comprehensivepre-configured virtual machines for data science modelling, development and deployment. https://azure.microsoft.com/en- us/services/virtual- machines/data-science-virtual- machines/
  • 19.
    Microsoft Research OpenData A collection of free datasets from Microsoft Research to advance state-of-the-art research in areas such as natural language processing, computer vision, and domain specific sciences. Download or copy directly to a cloud-based Data Science Virtual Machine for a seamless development experience. https://msropendata.com/
  • 20.
    AI School Dive inand learn how to start building intelligence into your solutions with the Microsoft AI platform, including pre-trained AI services like Cognitive Services and Bot Framework, as well as deep learning tools like Azure Machine Learning, Visual Studio Code Tools for AI, and Cognitive Toolkit. Our platform enables any developer to code in any language and infuse AI into your apps. Whether your solutions are existing or new, this is the intelligence platform to build on. https://aischool.microsoft.com/en-us
  • 21.