Articles

Ignite Announcements- Artificial intelligence

Image
AI for Humanitarian Action Microsoft is launching AI for Humanitarian Action, a new $40 million, five-year program that will harness the power of artificial intelligence for disaster recovery, helping children, protecting refugees and displaced people, and promoting respect for human rights. The company will partner with nongovernmental organizations through grants and investments of technology and expertise. AI for Humanitarian Action is part of Microsoft’s AI for Good initiative, a $115 million commitment to empowering people and organizations to solve global challenges with access to game-changing AI technology and educational opportunities, launched in July 2017.  Cortana Skills Kit for Enterprise Microsoft is bringing customizable Cortana experiences and skills with the new Cortana Skills Kit for Enterprise. The end-to-end solution allows enterprises to build custom skills and agents, test them with users and fully manage deployment to their organization. Develope

ChatBot

Image
How we   choose the bot framework ? If i talk about Microsoft. Essentially we have a single bot, is built and later rolled out to multiple canvasses without any further customization. Currently, the platform supports many channels (such as Facebook Messenger, Slack, SMS, email, Web Chat) including Microsoft’s own premiers (like Skype, Cortana, Microsoft Teams, Bing, GroupMe). All settings are pre-configured on the Developer Portal with an easy-to-follow walkthrough about how to integrate the bot with the hosting applications. How we   consume the bot framework ? Developers can connect directly from their client application, web chat controls or mobile apps throw Direct Line REST API tool of the bot Connector. This API makes it possible to empower existing applications and services with a conversational user interface. Microsoft has its own massive range of cloud-based Cognitive Services   APIs with the power of machine learning and AI algorithms. A developer can enhance

Cross-Origin Resource Sharing and Azure Machine Learning web services

Image
Cross-Origin Resource Sharing (CORS) is a mechanism that allows web objects (e.g., JavaScript) from one domain to request objects (web service requests) from another domain. Cross-origin requests initiated from scripts have been subject to restrictions primarily for security reasons. CORS provides a way for web servers to support cross-site access controls, which enable secure cross-site data transfers. At the time of this writing, it should be noted that Azure Machine Learning web services do not currently support CORS requests. See the following link for more information: https://social.msdn.microsoft.com/Forums/en-US/b6ddeb77-30e1-45b2-b7c1-eb4492142c0a/azure-ml-published-web-services-cross-origin-requests?forum=MachineLearning. This CORS restriction really means that if you wish to fully exploit Azure Machine Learning web services for deployment, testing, and production for a wide variety of (web) clients, you will need to host your own server-side applications. You basically hav

Create your first Azure Machine Learning experiment

Image
This post will helps you to create your first Azure Machine Learning workspace. For this you should log up with either a free or paid Azure subscription, or using the free trial Azure Machine learning offer. First open the Azure Management Portal https://manage.windowsazure.com ,  To create a new experiment you should click on +New in the bottom left corner of the screen, then you have a set of options to create :  Data Set : this option allows you to upload a new dataset to use with your experiment from a local file on disk Experiment: A Empty experiment or a preexisting experiment to help get you started fast I would like to start with a real exemple such as predicting whether a person’s income exceeds $50,000 per year based on his demographics or census data. You can imagine how incredibly useful the ability to predict a person’s income might be in the world of sales and marketing. This is exactly the kind of predictive analytics that would be most useful for a succes

Get started with Azure machine learning

Image
The first thing to get start with Azure Machine Learning journey is to get access to the Azure environnement, in this way we have 2 options : Option 1 : Trial offer :  http://azure.microsoft.com/en-us/pricing/free-trial  - With this offer allows you to get a $200 to spend on all Azure services only for one month  - This option will require youto apply using a Microsoft acoout and a valid credit card number for account verification purposes.  - During this month the Azure Managment Portal will prominently display your remaining trial credits  Option 2 :  http://azure.microsoft.com/en-us/pricing/free-trial - A free offer that allows you to access to the Azure Machine Learning environnement. - You need a valid Microsoft account  - Sign up for a Microsoft account visit :  http://windows.microsoft.com/en-US/windows-live/sign-up-create-account-how - if you are signed an introductory video is displayed if you like to take advantage of the free Azure Machine L

Azure Machine Learning Workflow

Image
The process of creating a Machine Learning on Azure  is composed of a many pattern of workflow steps. This workflow are designed to help users to create a new predictive alanytics in no limited time. The main steps in the process are summarized in this figure : Data :  Is your input, who will be acquired, compiled , analyzed, tested and trained Create the model :  There is a versious algorithms of machine learning. we should create a models who is capable to make predictions, based on interfaces about the datasets. Evaluate the model :  This step is so important in the process because we examine the accuracy of new predictive models based on ability to predict the correct outcome, when we know in advance the input and the output values. Accuracy is measured in terms of confidence factor approching the whole number one Refine and evaluate the model :  After evaluating the model we refine-it by comparing, contrasting and combining alternate predictive models to find th