课程详情

These practice sets are designed to empower professionals and students to confidently pass the AI-900: Microsoft Azure AI Fundamentals certification exam. Developed in line with the latest syllabus, they provide comprehensive and practical coverage of key AI concepts.By completing these practice sets, you will build expertise in:AI Workloads and Key Considerations: Learn how to identify and apply various AI scenarios.Machine Learning Fundamentals on Azure: Understand the core principles and capabilities of machine learning services.Computer Vision Workloads on Azure: Explore tools and techniques for image recognition and analysis.Natural Language Processing (NLP) on Azure: Gain insights into processing and analyzing text data.Conversational AI Workloads on Azure: Master the essentials of building and managing chatbots.Prepare confidently, upskill effectively, and achieve success with these targeted practice sets!Following topics/sub topics question covered in this practice sets so I would like to request you that before attempting this practice sets please go through each modules and its sub section.Describe Artificial Intelligence workloads and considerations (15-20%)Identify features of common AI workloads identify prediction/forecasting workloads identify features of anomaly detection workloads identify computer vision workloads identify natural language processing or knowledge mining workloads identify conversational AI workloadsIdentify guiding principles for responsible AI describe considerations for fairness in an AI solution describe considerations for reliability and safety in an AI solution describe considerations for privacy and security in an AI solution describe considerations for inclusiveness in an AI solution describe considerations for transparency in an AI solution describe considerations for accountability in an AI solutionDescribe fundamental principles of machine learning on Azure (30- 35%)Identify common machine learning types identify regression machine learning scenarios identify classification machine learning scenarios identify clustering machine learning scenariosDescribe core machine learning concepts identify features and labels in a dataset for machine learning describe how training and validation datasets are used in machine learning describe how machine learning algorithms are used for model training select and interpret model evaluation metrics for classification and regressionIdentify core tasks in creating a machine learning solution describe common features of data ingestion and preparation describe feature engineering and selection describe common features of model training and evaluation describe common features of model deployment and managementDescribe capabilities of no-code machine learning with Azure Machine Learning studio automated ML UI azure Machine Learning designerDescribe features of Natural Language Processing (NLP) workloads on Azure (15-20%)Identify features of common NLP Workload Scenarios identify features and uses for key phrase extraction identify features and uses for entity recognition identify features and uses for sentiment analysis identify features and uses for language modeling identify features and uses for speech recognition and synthesis identify features and uses for translationIdentify Azure tools and services for NLP workloads identify capabilities of the Text Analytics service identify capabilities of the Language Understanding service (LUIS) identify capabilities of the Speech service identify capabilities of the Translator Text serviceDescribe features of conversational AI workloads on Azure (15-20%)Identify common use cases for conversational AI identify features and uses for webchat bots identify common characteristics of conversational AI solutionsIdentify Azure services for conversational AI identify capabilities of the QnA Maker service identify capabilities of the Azure Bot servic

课程标签

0人关注该课程

主题相关的课程