AI-102 Study Notes

Notes for my Cloud certifications.

AI-102 Study Notes

Weightage of Domains:

General Concepts

Responsible AI

Selecting the Right Azure AI Services

Azure Cognitive Services

Vision Services

  1. Computer Vision
    • Image Analysis: Analyzes images to extract information such as objects, faces, and text. It supports operations like smart cropping, generating image descriptions, and tagging images.
    • Source: Azure AI Vision
  2. Azure AI Face service
    • Description: Detects and recognizes human faces in images and videos. It can identify facial attributes like age, emotion, and head pose, as well as perform face matching and verification.
    • Source: Azure AI Face
  3. Azure AI Document Intelligence
    • Description: Extracts text, key/value pairs, and tables from documents, such as receipts, invoices, and business cards. It allows you to build custom models to extract specific information.
    • Source: Azure AI Document Intelligence
  4. Custom Vision
    • Description: Enables you to build custom image classifiers and object detectors. You can upload images, tag them, and train models to recognize specific objects or scenes.
    • Source: Custom Vision
  5. Azure AI Video Indexer
    • Description: Extracts metadata and insights from video content, including face identification, text recognition, object detection, and scene segmentation.
    • Source: Azure AI Video Indexer

Speech Services

  1. Speech to Text
    • Description: Converts spoken language into written text, enabling transcription and real-time speech recognition.
    • Source: Azure Speech to Text
  2. Text to Speech
    • Description: Converts written text into natural-sounding speech, using neural voices that mimic human speech patterns.
    • Source: Azure Text to Speech
  3. Speech Translation
    • Description: Translates spoken language in real-time, providing both translated text and audio output in different languages.
    • Source: Azure Speech Translation

Language Services

  1. Text Analytics
    • Description: Extracts insights from text, including sentiment analysis, key phrase extraction, named entity recognition, and language detection.
    • Source: Azure Text Analytics
  2. Language Understanding (LUIS)
    • Description: Helps build natural language understanding into apps, bots, and IoT devices by allowing them to understand user intents and context. (LUIS will be retired on October 1st 2025 and starting April 1st 2023 you will not be able to create new LUIS resources. We recommend migrating your LUIS applications to conversational language understanding to benefit from continued product support and multilingual capabilities.)
    • Source: Azure LUIS
  3. Azure AI Translator
    • Description: Provides real-time text translation across multiple languages, supporting more than 60 languages for both standard and neural machine translation.
    • Source: Azure AI Translator

Decision Services

  1. Content Moderator
    • Description: Detects potentially offensive, risky, or unwanted content in text, images, and videos, providing automated moderation tools. Azure Content Moderator is deprecated as of February 2024 and will be retired by February 2027. It is replaced by Azure AI Content Safety, which offers advanced AI features and enhanced performance.
    • Source: Azure Content Moderator

Search Services

  1. Azure AI Search
    • Description: Azure AI Search (formerly known as “Azure Cognitive Search”) provides secure information retrieval at scale over user-owned content in traditional and generative AI search applications. Information retrieval is foundational to any app that surfaces text and vectors. Common scenarios include catalog or document search, data exploration, and increasingly chat-style apps over proprietary grounding data.
    • Source: Azure AI Search

Knowledge Services

  1. QnA Maker
    • Description: Creates a question-and-answer layer over your data, enabling natural language processing to respond to user queries from existing content like FAQs, manuals, and documents. The QnA Maker service is being retired on the 31st of March, 2025. A newer version of the question and answering capability is now available as part of Azure AI Language.
    • Source: Azure QnA Maker

Other Key Concepts

  1. Azure OpenAI
    • Description: Integrates powerful language models from OpenAI with Azure’s robust infrastructure, allowing you to implement advanced language understanding and generation capabilities. Azure OpenAI Service provides REST API access to OpenAI’s powerful language models including GPT-4o, GPT-4 Turbo with Vision, GPT-4, GPT-3.5-Turbo, and Embeddings model series.
    • Source: Azure OpenAI

Development and Deployment

Evaluation Metrics

Common Scenarios

Important Concepts to Keep in Mind