Wilson Mar bio photo

Wilson Mar

Hello. Hire me!

Email me Calendar Skype call 310 320-7878

LinkedIn Twitter Gitter Instagram Youtube

Github Stackoverflow Pinterest

How to run Cortana AI on Microsoft’s Azure cloud

Español (Spanish)   Français (French)   Deutsch (German)   Italiano   Português   Cyrillic Russian   中文 (简体) Chinese (Simplified)   日本語 Japanese   한국어 Korean


This article provides a guided tour of use Microsoft’s AI (Artificial Intelligence) offerings, which include Machine / Deep Learning capabilities running on the Azure cloud.



In 2014, Microsoft showed off its facial recognition capabilities with how-old.net to guess how old someone is. At conferences they built a booth that takes a picture.

In 2015, Microsoft unleashed the Tay chat bot, then had to bring it down after hackers submitted enough racial slurs that they fooled the system into thinking that was normal and acceptable.

In April 2018 Microsoft reorganized into two divisions that offers AI:

  • The research division, headed by Harry Shum, is putting AI into Bing search, Cortana voice recognition and text-to-speech, ambient computing, and robotics.

  • Microsft’s “computing fabric” offerings, led by Scott Guthrie, makes AI services available for those building customizable machine learning with speech, language, vision, and knowledge services. Tools offered include Cognitive Services and Bot Framework, deep-learning tools like Azure Machine Learning, Visual Studio Code Tools for AI, and Cognitive Toolkit.

Microsoft’s Azure IoT Edge (at https://github.com/Azure/ai-toolkit-iot-edge) brings AI and machine learning to the edge of networks, such as in the field and on factory floors. See the Sample app and read all the unanswered forum posts

  • https://channel9.msdn.com/events/Build/2018/BRK2154

Project Brainwave

At Build 2018, Microsoft announced Project Brainwave to run Google’s Tensorflow AI code and Facebook’s Caffe2, and Microsoft’s Cognitive Toolkit.

[ This pdf white paper says the “high-performance, precision-adaptable FPGA soft processor is at the heart of the system, achieving up to 39.5 TFLOPs of effective performance at Batch 1 on a state-of-the-art Intel Stratix 10 FPGA.” Microsoft’s use of field programmable gate arrays (FPGA) calculates AI reportedly “five times faster than Google’s TPU hardware”.

“Each FPGA operates in-line between the server’s network interface card (NIC) and the top-of-rack (TOR) switch, enabling in-situ processing of network packets and point-to-point connectivity between hundreds of thousands of FPGAs at low latency (two microseconds per switch hop, one-way).”

Documentation on CNTK is at https://docs.microsoft.com/en-us/cognitive-toolkit/index

https://docs.microsoft.com/en-us/cognitive-toolkit/brainscript-basic-concepts BrainScript uses a C-like syntax that is aimed at allowing to express neural networks in a way that looks like math formulas. BrainScript is dynamically typed.

Brainscript has a Performance Profiler that can be enabled.

Hyper-parameters are a separate module (alongside Network and reader) to perform SGD (stochastic-gradient descent).



Subject matter

There is dual approach to understanding and using AI/Machine Learning:

  • Use cases for specific industries/problem areas
  • Tools (Algorithms)

AI Use Cases

Case studies of how people are already making use of AI/ML to save time and money:

  • Predictive Maintenance data science webinar
  • Defect Detection with Image Analysis
  • Custom Entity Extraction with Text Analytics

XiaoIce, a chatbot Microsoft launched in China, “has more than 200 million users, has engaged in 30 billion conversations, and has an average conversation length of 23 turns, which averages out to about half an hour, achieving human parity at translation from Chinese to English. Japan-based Rinna and the US-based Zo)

FATE and Ethical Principles

Microsoft has a FATE (Fairness, Accountability, Transparency, and Ethics) research group:

  • Fairness: AI systems should treat all people fairly.
  • Accountability: AI systems should have algorithmic accountability.
  • Transparency: AI systems should be understandable.

But who else is looking out for the other Microsoft’s ethical principles guiding the development and use of artificial intelligence with people:

  • Reliability & Safety: AI systems should perform reliably and safely.
  • Inclusiveness: AI systems should empower everyone and engage people.
  • Privacy & Security: AI systems should be secure and respect privacy.


  1. Take the introductory tutorial:

    Introduction to Machine Learning with Hands-On Labs


  2. Create a model.

  3. Prepare Data:

    As per this video using

    • Clean Missing Data - Clip Outliers
    • Edit Metadata
    • Feature Selection
    • Filter
    • Learning with Counts
    • Normalize Data
    • Partition and Sample
    • Principal Component Analysis
    • Quantize Data
    • SQLite Transformation
    • Synthetic Minority Oversampling Technique

  4. Train the model

    • Cross Validation
    • Retraining
    • Parameter Sweep

  5. Score and test the model.

  6. Make predictions with Elastic APIs

    • Request-Response Service (RRS) Predictive Experiment - Batch Execution Service (BES)
    • Retraining API


Fraud Detection with Azure HDInsight Spark Clusters

Loan Credit Risk with Azure HDInsight Spark Clusters

Loan ChargeOff Prediction with Azure HDInsight Spark Clusters

Data Science VM



This is one of a series on AI, Machine Learning, Deep Learning, Robotics, and Analytics:

  1. AI Ecosystem
  2. Machine Learning
  3. Testing AI

  4. Microsoft’s AI
  5. Microsoft’s Azure Machine Learning Algorithms
  6. Microsoft’s Azure Machine Learning tutorial
  7. Microsoft’s Azure Machine Learning certification

  8. Python installation
  9. Juypter notebooks processing Python for humans

  10. Image Processing
  11. Tessaract OCR using OpenCV
  12. Amazon Lex text to speech

  13. Code Generation

  14. Multiple Regression calculation and visualization using Excel and Machine Learning
  15. Tableau Data Visualization