AI - 100 Designing and Implementing an Azure AI Solution
- Understand how to analyze different business scenarios and translate them into different tools available
- Understand how to design a solution using Cognitive Services
- Understand bot services and LUIS and how to design a solution using these technologies
- Understand the various High Performance Computing solutions that rely on computer infrastructure within the cloud, on-premises, and within hybrid scenarios
- Understand security, compliance, and governance as it pertains to designing an AI solution in the cloud
• Ingestion is the first step in the AI process, because data can come from various technologies and tools, such as IoT solutions, batch processing solutions, or third-party applications. In this section, we will discuss the tools available to ingest data and when to use them, such as IoT Hub, Event Hubs, and Azure Data Lake Store.
• Processing and cleaning of data, so that the data can be fed into models and other AI tools is important to help gain and understanding and feed the proper type of data to the users. In this section, we will discuss HDInsight, Stream Analytics, and Databricks and the use cases involved for these various processing solutions.
• Once the data is processed it must get stored in some type of data store in Azure, so that it can be fed into analytics tools for reports or other applications for classification and recommendation purposes. In this section, we will discuss relational and non-relational databases and when to use each type of database available in Azure.
In previous sections we discussed the various business scenarios available to use Cognitive Services. In this module, we will now design a solution using Cognitive Services.
• In this section, we will discuss how to integrate your AI solutions using various Cognitive services from Vision APIs, Search APIs, Speech APIs, Language APIs, and the Decision APIs.
• In this section, we will discuss the bot framework and how it integrates with AI solutions.
• In this section, we will discuss how LUIS can be used in different use cases to help with language understanding within the bot framework as users input data into solutions.
• In this section, we will discuss how the bot framework can be used to integrate with different services through Channels, such as Skype, Facebook, and other messaging services.
• In this section, we will discuss how to take your bot and tie it into Application Services and Application Insights to create an end to end bot solution.
• In this section, we will discuss the different reasons to use a GPU, FPGA, or CPU intensive machine to create various AI solutions in the cloud. Deep Learning solutions will be covered in this section.
• In this section, we will discuss various use cases that identify when you should create a solution in the cloud versus on-premises or using a hybrid computing infrastructure.
• In this section, we will discuss the various cost implications involved in creating an AI solution using IaaS, Hybrid, and on-premises and how it affects your solution choice.
• In this section, we will discuss the various security and authentication mechanisms available for your AI solutions and reasons to use these various solutions.
• In this section, we will discuss how to implement a data governance policy and enforce it with various technologies within the cloud.
• In this section, we will discuss tools available to check that your data security policies are setup to adhere to your data governance policies and compliance restrictions.
Start a free trial
Skill Me Up subscriptions include unlimited access to on-demand courses with live lab lab environments with our Real Time Labs feature for hands-on lab access.
- Access to Real Time Lab environments and lab guides
- Course Completion Certificates when you pass assessments
- MUCH MORE!