AI Dictionary

Artificial Intelligence

Computer systems designed to perform tasks that normally require aspects of human intelligence, such as understanding, reasoning or recognizing patterns.

Machine Learning

Techniques in which models learn patterns from data instead of being explicitly programmed for every task.

Deep Learning

A type of machine learning based largely on multi-layer neural networks that can learn complex patterns from large amounts of data.

Generative AI

AI systems capable of generating content such as text, images, audio, video or code.

LLM

Large Language Model, an AI model trained on large amounts of text to understand and generate human language.

Prompt

An instruction or input supplied to an AI system to guide the response or output it produces.

Hallucination

An inaccurate AI output that can appear confident or plausible even though the information is incorrect or unsupported.

RAG

Retrieval-Augmented Generation, a pattern that retrieves relevant information before generating an answer.

Algorithm

A defined set of steps or rules used to solve a problem or perform a computation.

Dataset

A collection of data used for tasks such as training, evaluating or testing an AI model.

Model

A trained computational system that has learned patterns from data and can use those patterns to produce predictions or outputs.

Training

The process of adjusting a model using data so that it learns patterns useful for a particular task.

Inference

The process of using a trained AI model to produce an output from new input.

Parameter

A value learned by a model during training that influences how the model processes input and produces output.

Neural Network

A machine learning model made of connected computational units that can learn patterns from data.

Natural Language Processing

The field of AI concerned with enabling computers to process, understand and generate human language.

Computer Vision

A field of AI that enables computers to analyze and interpret information from images and video.

Transformer

A neural network architecture that uses attention mechanisms to process relationships between parts of an input.

Token

A unit of text processed by a language model. A token may represent a whole word, part of a word, punctuation or another piece of text.

Embedding

A numerical representation of information that captures relationships and similarities between pieces of data.

Fine-tuning

Additional training of an existing model on a more specific dataset to adapt it for a particular task or purpose.

Foundation Model

A large model trained on broad data that can serve as a base for many different applications and tasks.

Multimodal AI

AI that can work with more than one type of information, such as text, images, audio or video.

AI Agent

An AI system designed to carry out tasks by interpreting goals, making decisions and using available tools or actions.