Artificial Intelligence (AI) is increasingly at the core of modern apps and services. In this module, you’ll learn about some common AI capabilities that you can leverage in your apps, and how those capabilities are implemented in Microsoft Azure. You’ll also learn about some considerations for designing and implementing AI solutions responsibly.

Cognitive Services are the core building blocks for integrating AI capabilities into your apps. In this module, you’ll learn how to provision, secure, monitor, and deploy cognitive services.

Natural Language processing (NLP) is a branch of artificial intelligence that deals with extracting insights from written or spoken language. In this module, you’ll learn how to use cognitive services to analyze and translate text.

Many modern apps and services accept spoken input and can respond by synthesizing text. In this module, you’ll continue your exploration of natural language processing capabilities by learning how to build speech-enabled applications.

To build an application that can intelligently understand and respond to natural language input, you must define and train a model for language understanding. In this module, you’ll learn how to use the Language Understanding service to create an app that can identify user intent from natural language input.

One of the most common kinds of interaction between users and AI software agents is for users to submit questions in natural language, and for the AI agent to respond intelligently with an appropriate answer. In this module, you’ll explore how the QnA Maker service enables the development of this kind of solution.

Bots are the basis for an increasingly common kind of AI application in which users engage in conversations with AI agents, often as they would with a human agent. In this module, you’ll explore the Microsoft Bot Framework and the Azure Bot Service, which together provide a platform for creating and delivering conversational experiences.

Computer vision is an area of artificial intelligence in which software applications interpret visual input from images or video. In this module, you’ll start your exploration of computer vision by learning how to use cognitive services to analyze images and video.

While there are many scenarios where pre-defined general computer vision capabilities can be useful, sometimes you need to train a custom model with your own visual data. In this module, you’ll explore the Custom Vision service, and how to use it to create custom image classification and object detection models.

Facial detection, analysis, and recognition are common computer vision scenarios. In this module, you’ll explore the user of cognitive services to identify human faces.

Optical character recognition (OCR) is another common computer vision scenario, in which software extracts text from images or documents. In this module, you’ll explore cognitive services that can be used to detect and read text in images, documents, and forms.

Ultimately, many AI scenarios involve intelligently searching for information based on user queries. AI-powered knowledge mining is an increasingly important way to build intelligent search solutions that use AI to extract insights from large repositories of digital data and enable users to find and analyze those insights.