Course Overview
The Introduction to AI in Azure (AI-901T00-A) course provides a foundational understanding of artificial intelligence (AI) concepts and the technologies used to develop AI solutions with Microsoft Azure. Designed for learners beginning their journey in AI solution development, the course introduces essential concepts and terminology across common AI workloads.
Learners explore generative AI and AI agents, natural language processing (NLP), speech, computer vision, information extraction, responsible AI, and retrieval-augmented generation (RAG). The course also introduces large language models (LLMs), prompting, speech recognition and synthesis, modern computer vision techniques, optical character recognition (OCR), and methods for grounding generative AI responses in relevant information.
Practical exercises reinforce key concepts by allowing learners to explore common AI workloads. The course also supports preparation for the AI-901: Microsoft Azure AI Fundamentals exam.
Course Objective
- Understand fundamental AI concepts, terminology, common workloads, and responsible AI principles.
- Explain the fundamentals of generative AI, large language models (LLMs), prompts, and AI agents.
- Describe natural language processing concepts, including tokenization, statistical text analysis, and semantic language models.
- Explain AI speech concepts, including speech-enabled solutions, speech recognition, and speech synthesis.
- Identify common computer vision tasks, image-processing techniques, and modern vision models.
- Describe convolutional neural networks, vision transformers, multimodal models, and image generation concepts.
- Explain how AI can extract information from documents, images, and other unstructured data sources.
- Describe optical character recognition (OCR), field extraction, and mapping concepts.
- Explain retrieval-augmented generation (RAG), including data preparation, information retrieval, response generation, and evaluation.
- Apply foundational AI concepts through exercises covering common AI workloads.
Pre-requisites
Learners should have a basic understanding of computing concepts and mathematics. Familiarity with Python coding syntax and programming techniques is useful but not mandatory. Knowledge of core cloud concepts, including cloud storage, cloud compute, authentication, and authorization, is recommended.
Course Curriculum
Introduction to AI; Generative AI and agents; Text and natural language; Speech; Computer vision; Information extraction; Responsible AI; Exercise – Explore AI workloads; Module assessment; Summary.
Introduction; Large language models (LLMs); Prompts; AI agents; Exercise – Explore generative AI; Module assessment; Summary.
Introduction; Tokenization; Statistical text analysis; Semantic language models; Exercise – Explore text analytics; Module assessment; Summary.
Introduction; Speech-enabled solutions; Speech recognition; Speech synthesis; Exercise – Explore AI speech; Module assessment; Summary.
Introduction; Computer vision tasks and techniques; Images and image processing; Convolutional neural networks; Vision transformers and multimodal models; Image generation; Exercise – Explore computer vision; Module assessment; Summary.
Introduction; Overview of information extraction; Optical character recognition (OCR); Field extraction and mapping; Exercise – Explore AI information extraction; Module assessment; Summary.
Introduction; Understand retrieval-augmented generation; Prepare data for retrieval; Retrieve information and generate a response; Evaluate a RAG solution; Exercise – Explore RAG; Module assessment; Summary.
