Term 91
Object detection
Object detection is a computer vision technology that identifies and locates specific objects within an image or video.
Acronym study
Terms 91–120 of 150 AI-900 acronyms and key terms. Each entry includes a plain-English definition and a link to the full 800-word glossary page with exam context and practice questions.
Term 91
Object detection is a computer vision technology that identifies and locates specific objects within an image or video.
Term 92
Optical Character Recognition is technology that converts images of text, like scanned documents or photos, into machine-readable text data.
Term 93
OpsCenter is a centralized management platform used to monitor, deploy, and orchestrate IT infrastructure and applications across multiple environments.
Term 94
OSINT (Open Source Intelligence) is the practice of collecting and analyzing publicly available information from free or commercially available sources to support intelligence gathering, cybersecurity assessments, and penetration testing.
Term 95
Overfitting occurs when a machine learning model learns the training data too well, including its noise and outliers, causing it to perform poorly on new, unseen data.
Term 96
Parameter Store is a secure, centralized service for storing and managing configuration data, secrets, and environment variables used by applications and IT infrastructure.
Term 97
Passive reconnaissance is the process of gathering information about a target system or network without directly interacting with it, using publicly available sources and stealthy observation.
Term 98
A Patch Manager is a tool or service that automates the process of finding, downloading, testing, and installing software updates across multiple computers to keep them secure and stable.
Term 99
A logical grouping of cloud instances placed close together or spread apart to optimize performance, fault tolerance, or network latency.
Term 100
A pod is the smallest deployable unit in Kubernetes, containing one or more containers that share storage, network, and a specification for how to run.
Term 101
Port scanning is the process of probing a computer or network device to discover which network ports are open, closed, or filtered, revealing potential entry points for services and applications.
Term 102
Prediction is the process of using data and algorithms to forecast future outcomes or identify patterns without explicit programming for each scenario.
Term 103
Privacy and security refer to the practices and technologies used to protect sensitive data from unauthorized access while ensuring individuals' rights over their personal information are respected.
Term 104
A profiler is a tool that monitors and analyzes the performance, resource usage, and behavior of software applications or systems to identify bottlenecks and optimize efficiency.
Term 105
Prompt engineering is the practice of designing and refining input queries to AI models to get the most accurate, relevant, and useful outputs.
Term 106
Provisioned concurrency is a feature in serverless computing that keeps a specified number of function instances initialized and ready to respond immediately, eliminating cold start delays.
Term 107
Question answering is an Azure AI service that lets you build a natural language query system that extracts answers from a custom knowledge base of documents or FAQs.
Term 108
Retrieval-Augmented Generation (RAG) is a technique that combines information retrieval with text generation to produce more accurate and contextually relevant answers from large language models.
Term 109
A read replica is a copy of a database that is used only to handle read queries, taking load off the primary database.
Term 110
Regression is a type of machine learning algorithm that predicts a continuous numeric output based on input data, used to model relationships between variables.
Term 111
Reinforcement learning is a machine learning approach where an agent learns to make decisions by taking actions in an environment to maximize cumulative reward.
Term 112
Reliability and safety in IT means that systems consistently perform their intended functions without failure and that they operate without causing harm to people, data, or the environment.
Term 113
A Reserved Instance is a billing discount applied to your usage of virtual machines or other compute resources when you commit to using a specific configuration for a one- or three-year term.
Term 114
A framework of ethical principles and practices that ensure artificial intelligence systems are developed and deployed in a transparent, fair, accountable, and safe manner.
Term 115
Retrieval augmented generation (RAG) is a technique that combines information retrieval with text generation to produce more accurate and contextually relevant answers.
Term 116
A Route 53 health check is a feature of Amazon Route 53 DNS service that monitors the availability and performance of an endpoint, such as a web server, from multiple global locations to automatically route traffic away from failures.
Term 117
The Run command is a built-in feature in Windows operating systems that allows you to quickly open programs, files, folders, and system tools by typing a specific command or path directly into a small dialog box.
Term 118
A flexible pricing model from cloud providers that gives you discounted rates on compute usage in exchange for a commitment to a consistent amount of spending over a one- or three-year term.
Term 119
Scheduled scaling is a cloud computing strategy that automatically adjusts computing resources based on a predefined time schedule to match predictable workload patterns.
Term 120
A search index is a data structure that stores a mapping of content to locations, enabling fast and efficient information retrieval in search systems.