CertifyDeckCargando contenido…
The official Microsoft Certified: Azure AI Fundamentals syllabus, organized by domain. Check off each point as you review it.
Inicia sesión para guardar tu progreso entre sesiones.
Describe principles of responsible AI
Fairness means an AI system must not treat similar people or groups differently. Because people choose the data and it can carry unconscious bias, developers minimize bias in training data and test results across sensitive groups, for example with the fairness assessment in the Responsible AI dashboard.
Responsible AI - Training ↗What is Responsible AI - Azure Machine Learning ↗
AI is based on probabilistic models and is not infallible, so applications must mitigate its risks: work as designed, respond safely to unexpected conditions and avoid acting when confidence is low. Content filters help, but the principles apply from design through operation.
Responsible AI - Training ↗What is Responsible AI - Azure Machine Learning ↗
Models are trained on data that may include personal information, so that data must be kept secure and the trained model must not reveal private details. This is applied with access control, encryption in transit and at rest, auditing, deleting data no longer needed, and tools such as SmartNoise (differential privacy) and Counterfit.
What is Responsible AI - Azure Machine Learning ↗Responsible AI - Training ↗
Inclusiveness means the potential of AI is open to everyone and solutions do not exclude any user. In practice, a speech-based agent also offers text captions, and agent design considers accessibility, language variation and different levels of technical proficiency, with input from diverse communities from the start.
Responsible AI - Training ↗Responsible AI for agent design ↗
Transparency means users know how an AI system works and what limitations it has: stating that AI is used, describing features of the training data without revealing confidential information, and providing Transparency Notes or in-product disclosures. Interpretability (global, local and cohort explanations) helps people understand its decisions.
Responsible AI - Training ↗What is Responsible AI - Azure Machine Learning ↗
Accountability requires that the people who design and deploy an AI system answer for how it operates, and that AI is not the final authority on decisions that affect people. It relies on industry norms, human oversight, lifecycle traceability (MLOps), reports such as the scorecard, and incident response plans.
What is Responsible AI - Azure Machine Learning ↗Overview of Responsible AI practices for Azure OpenAI in Foundry Models ↗
Identify AI model components and configurations
Generative language models split text into tokens, turn them into embeddings with a transformer (an encoder using attention), and a decoder predicts the most probable continuation of a prompt one token at a time. Examples in a prompt condition only that inference, and the app resends history to give context.
Large language models (LLMs) - Training ↗Prompts - Training ↗
Choosing a model starts with the task: embeddings for semantic search, multimodal models to analyze images with text, image or video models to generate content, small models for lightweight apps and fast models for high-volume chat. For a well-defined case, a Foundry tool with prebuilt models gives more predictable results.
Generative AI models - Training ↗Multimodal models for image analysis - Training ↗
When you deploy a model you choose the deployment type (Global Standard by default, Data Zone or Standard for residency, Provisioned for reserved capacity, Batch for asynchronous jobs), the version and the tokens per minute. Temperature, top_p and max output tokens are adjusted in the playground or in code.
Understanding deployment types in Microsoft Foundry Models ↗Using a generative AI model - Training ↗
Identify AI workloads
Common workloads are generative AI and agents (a model, instructions and tools that act), text analysis (sentiment, key phrases, entities, PII), speech (recognition, synthesis and speech-to-speech), vision (image analysis and generation), and information extraction from documents, audio and video using schemas.
AI agents - Training ↗Introduction - Get started with AI-powered information extraction in Azure ↗
Key phrase extraction lists the main concepts of a text, entity recognition detects and classifies items such as people, places, dates or quantities, and sentiment analysis labels sentences and documents as positive, neutral or negative with confidence scores. Summarization can be extractive (original sentences) or abstractive (newly written wording).
What is Azure Language in Foundry Tools ↗What is summarization? ↗
Speech recognition (speech to text) converts audio into text through an acoustic model and a language model, and can run in real time, fast or in batch, with custom models for specific vocabulary. Speech synthesis (text to speech) produces audio with neural voices and is tuned with SSML. Voice Live joins both for real-time conversations with an agent.
Vision-enabled multimodal models accept images and text in one request (as URL or base64) to describe photos and answer questions about them. Image generation models create pictures from text, and video generation models produce clips through asynchronous jobs. Azure Vision adds OCR and Face for reading text and analyzing faces.
Multimodal models for image analysis ↗Image generation models ↗
Azure Content Understanding in Foundry Tools turns documents, images, audio and video into structured data through analyzers with a field schema, going beyond basic OCR. Audio analyzers transcribe with diarization, and video analyzers add key frames, shots and segments. Plain text is analyzed with Azure Language, for example with entity recognition.
What is Azure Content Understanding in Foundry Tools? ↗Extract information from documents ↗