Machine Learning in Azure

Image Credits : Digital Ocean

Machine learning is a method of data analysis that automates analytical model building. It's a branch of Artificial Intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human interaction.

Two most widely adopted machine learning methods are,

• Supervised learning: algorithms are trained using labeled examples, such as an input where the desired output is known.
• Unsupervised learning: is used against data that has no historical labels. The system is not told the "right answer." The algorithm must figure out what is being shown. 

Differences between data mining, machine learning and deep learning

• Data mining is about to identify previously unknown patterns from data. It might involve traditional statistical methods and machine learning.
• Deep learning combines advances in computing power and special types of neural networks to learn complicated patterns in large amounts of data. Deep learning techniques are currently state of the art for identifying objects in images and words in sounds

Following example is a simple tutorial into machine learning using ML.NET, uses Iris Data Set which can be used to predict type of iris flower.

Announcing ML.NET Latest Version 0.7 (Machine Learning .NET).
Was released newly in November 2018, It has Enhanced support for recommendation tasks with Matrix Factorization, Enabled anomaly detection scenarios – detecting unusual events, Improved customizability of ML.NET pipelines and few more. 

Cognitive Services in Azure

Cognitive services in azure covers,

Vision

Image-processing algorithms to smartly identify, caption and moderate your pictures.

Computer Vision: 

Extract rich information from images to categorize and process visual data—and perform machine-assisted moderation of images to help curate your services.

• Read text in images
• Recognize celebrities and landmarks
• Analyze video in near real-time
• Generate a thumbnail

Face API : 

Detect human faces, compare similar ones, Organize based on attributes, Identify previously tagged people

Other Cognitive service categories and services include, 

Speech : Features include speech to text, speaker recognition, text to speech

Language : Text Analytics, Text translate, Content moderator

Knowledge : QnA Maker

You can use https://www.qnamaker.ai/ to create a Q and A and integrate it with bot framework. Then you can embed it in sites

Search : Bing Search

Azure Databricks (link)

Azure Databricks is an Apache Spark-based analytics platform optimized for the Microsoft Azure cloud services platform.

Take a look at How Databricks makes big data simple and Databricks FAQ for more information on this. Azure tutorial here.

Conversational 

Bot Service

Data Science VMs

Pre-configured with popular tools for data science

AI Frameworks

• Tensorflow
• Azure Cognitive Toolkit

Machine learning in AWS

https://aws.amazon.com/machine-learning

Practical Use Cases

https://yalantis.com/blog/predictive-algorithm-for-house-price/

https://microsoft.github.io/techcasestudies/iot/2017/05/05/KingwaytekIoT.html