Skip to main content

Machine Learning in Azure

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.

This series of articles intend to elaborate the usage of Azure Machine learning and usage of different machine learning tools in Azure ML studio. This is the first post and it walks you through the introduction to the Azure ML studio and how to upload data to the tool.

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.

Cognitive Services in Azure

Vision

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

Computer Vision    - Analyse content in images and video.
Custom Vision        - Customize image recognition to fit your business needs.
Face                      - Detect and identify people and emotions in images.
Form Recogniser    - Extract text, key-value pairs and tables from documents.
Video Indexer        - Analyze the visual and audio channels of a video, and index its content.

APIs for AI related to vision example https://azure.microsoft.com/en-gb/services/cognitive-services/#api

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

I hope this has been informative and thank you for reading!

Labels:

Comments

Post a Comment

Popular posts from this blog

Azure Traffic Manager (ATM)

Azure Traffic Manager is a DNS-based traffic load balancer that enables you to distribute traffic optimally to services across global Azure regions while providing high availability and responsiveness. The traffic manager service is used to direct client requests to the most appropriate service endpoint that is based on a traffic routing method and health of the endpoint. The different traffic routing methods available for the Azure Traffic Manager below Priority: Route traffic to another endpoint in case the primary falls. Weighted: Route traffic to the different endpoints based on weight. Performance: You want the end-users to use the "closest" endpoint in terms of the lowest network latency. Geographic: Users would be directed to the endpoint based on their geographic location. Subnet: This maps the set of end-users IP address ranges to a specific endpoint within a traffic manager profile. I hope this has been informative and thank you for reading!
Post a Comment
Read more

Azure Landing Zone – Networking Overview

In this blog post, we will be going through the networking overview of the Azure Landing Zone. key design considerations and recommendations surrounding network typologies in Microsoft Azure. Design Element : Below are the design consideration for Azure networking and connectivity. Planning for IP Addressing Configure DNS Define an Azure Networking Topology Connectivity to Azure Connectivity to other cloud providers Planning for IP Addressing IP address planning is a vital first step when designing a network in Azure especially if you have a hybrid environment to avoid overlapping IP address space across on-premises environment and Azure. Design Considerations: Azure reserves 5 IP address with each subnet so factor in the address space when sizing the virtual networks. Some Azure service such as Application Gateway – WAF, Azure Firewall, Azure Bastion and VPN Gateway require dedicated subnets. You can delegate subnets to some Azure service that can be injected into the virtual network....
Post a Comment
Read more

Azure Networking

Azure Network service connect cloud and on-premises infrastructure, to provide your customers and users the best possible experience Also, support your hybrid or all-in cloud strategy using networking services built on one of the largest fiber network backbones. Get the most from your Azure or open-source solutions and workloads with highly reliable performance and secure connectivity. Listed network services are available in Azure currently. Azure Virtual Network Azure Load Balancer Azure Traffic Manager Azure Express Route Azure VPN Gateway Azure DNS Azure Content Delivery Network  Azure Virtual WAN I hope this has been informative and thank you for reading! 
Post a Comment
Read more