19 terms
Na system wey dem don train with data; e use wetin e learn to make prediction, choose answer, or create content.
A trained mathematical system that uses patterns learned from data to produce predictions, decisions, or generated content.
Na clear steps or rules wey computer dey follow to solve problem or finish one work.
A defined set of steps or rules a computer follows to solve a problem or complete a task.
Na computer system wey dem design to do some work wey normally need human sense, like to notice patterns, understand language, or suggest wetin person fit do.
Computer systems designed to perform tasks that usually require human intelligence, such as recognizing patterns, understanding language, or making recommendations.
Na task wey AI dey put something inside one or more group wey dem don decide before, like mark email as spam or no be spam.
A task where an AI system assigns an item to one or more predefined categories, such as labeling an email as spam or not spam.
Na area of AI wey dey help computer check and understand picture and video.
A field of AI that helps computers analyze and make sense of images and video.
Na collection of data wey dem arrange together to train, test, or check how AI dey perform.
An organized collection of data used to train, test, or evaluate an AI system.
Na machine learning wey use neural network wey get plenty layers to learn difficult patterns from plenty data.
A type of machine learning that uses many-layered neural networks to learn complex patterns from large amounts of data.
Na set of numbers wey represent meaning or features of text, picture, or other data, so computer fit compare dem with calculation.
A list of numbers that represents the meaning or features of text, images, or other data so a computer can compare them mathematically.
Na AI wey fit create new things like text, picture, sound, video, or code, based on pattern wey e don learn from data.
AI that creates new content, such as text, images, audio, video, or code, based on patterns learned from data.
Na when you use AI model wey don train to produce answer, prediction, or put something inside one group.
The process of using a trained AI model to produce an output, such as an answer, prediction, or classification.
Na AI model wey dem train with plenty text so e fit understand and produce language. E dey use wetin e learn and the question wey you ask am to form likely answer.
An AI model trained on large amounts of text to understand and generate language. It produces likely continuations based on its training and input.
Na one way to build AI wey dey learn pattern from examples or data, instead of following only rules wey person write by hand.
A way of building AI systems that learn patterns from examples or data instead of following only hand-written rules.
Na AI wey fit work with more than one kind information, like text, picture, sound, or video.
AI that can work with more than one type of information, such as text, images, audio, or video.
Na area of AI wey dey help computer work with human language, like to read, understand, or produce text and speech.
A field of AI that helps computers work with human language, including reading, understanding, and generating text or speech.
Na computer method wey get connected units for different layers. E dey learn how things for data relate; the idea get small likeness to how brain dey work.
A computing method made of connected units arranged in layers that learn relationships in data, loosely inspired by the brain.
Na guess about wetin fit happen or result wey person never know, based on pattern wey dey inside available data.
An estimate about a future or unknown result based on patterns in available data.
Na system wey dey suggest things or action wey person fit like or find useful, based on things wey e choose before or wetin similar people like.
A system that suggests items or actions a person may like or find useful, based on data such as past choices or similar users.
Na small piece of text wey language model dey process. E fit be full word, part of word, or punctuation sign; e no always be one complete word.
A small piece of text, such as a word, part of a word, or punctuation, that a language model processes. Tokens are not always whole words.
Na examples and information wey dem give AI make e learn pattern or how to do one task.
Examples and information used to teach an AI model patterns or tasks during training.