Wednesday, November 2, 2016

Supervised Learning ML


Supervised learning is a type of machine learning algorithm that uses a known dataset (called the training dataset) to make predictions. 

The training dataset includes input data and response values. From it, the supervised learning algorithm seeks to build a model that can make predictions of the response values for a new dataset. A test dataset is often used to validate the model. Using larger training datasets often yield models with higher predictive power that can generalize well for new datasets.

Supervised learning includes two categories of algorithms:

Tuesday, November 1, 2016

Intents, Entities, and Model Training LUIS


One of the key problems in human-computer interactions is the ability of the computer to understand what a person wants, and to find the pieces of information that are relevant to their intent. 




Ex : " Get the stock price for msft". In this case the intent is to get the stock price of the company and entity is msft.

Intent -> What we want to do.
StockPrice
IstheMarketUpOrDown
RepeatLastStock

Entity -> an object that exists and is distinguishable from other objects

Sunday, October 30, 2016

Overview of LUIS ( Language Understanding Integration Services )

Is a service provided by Microsoft cognitive services, Formally known as project Oxford.They are a set of intelligent services with the vision of democratizing machine learning. 




Monday, October 24, 2016

MessageController in Bot Framework

  The Message Controller is the meat of  Bot application

  • It resides in an asp.net application
  • It can accept a message and return a message
The message controller monitors the different activities of the User

The default type of activity is is Activity.message. 

Friday, October 7, 2016

Azure app services




 Azure App Service, a cloud service that bundles together several existing ones: Azure Websites,  Azure Mobile Services, and Azure BizTalk Services 
  • Provides services that can be used to build many applications
  • Offers these services as capabilities that can be used without having to worry about plumbing servers
  • Enables us to focus on adding business values

Advantages of Microsoft Azure



  • Ease of use 
    • We do not need physical hardware
    • Certain cloud services do not need servers
  • Scalability. We can easily scale up or down based on the need
  • Pay for what we use

Tuesday, October 4, 2016

Getting started with Microsoft bot connector

The Microsoft Bot Connector is a communication service that  helps you connect your Bot with many different communication channels (Skype, SMS, email, and others)


If you write a conversational Bot or agent and expose a Microsoft Bot Framework-compatible API on the Internet, the Bot Framework Connector service will forward messages from your Bot to a user, and will send user messages back to your Bot.