18 terms / All
Artificial Intelligence (AI)
The broad field of building systems that can perform tasks usually associated with human intelligence, such as recognizing speech, making decisions, or translating language.
Machine Learning (ML)
A subset of AI in which systems learn patterns from examples rather than being explicitly programmed with a rule for every situation.
Deep Learning
A specialized kind of machine learning that uses neural networks with many layers to find patterns in large amounts of data.
Neural Network
A layered arrangement of connected computing units that process information and learn patterns from data.
Algorithm
A defined set of instructions a computer follows to solve a problem or learn from data.
Black Box
A system whose inputs and outputs are visible, but whose internal decision process can be difficult to understand.
Generative AI
AI that produces new material, such as text, images, audio, or code, based on patterns learned during training.
Large Language Model (LLM)
A model trained on large amounts of text to understand, summarize, and generate language.
Transformer
The architecture behind many modern language models. Its attention mechanism helps a model weigh relationships across text.
Prompt
The input or instruction you give an AI system to guide its response. Specific context usually leads to more useful output.
Token
A unit of text a model processes. A token may be a word, part of a word, or punctuation.
Context Window
The amount of information a model can consider in a given interaction—its working space for that conversation.
Hallucination
When an AI generates an answer that sounds convincing but is inaccurate or invented. Important outputs always need verification.
Retrieval-Augmented Generation (RAG)
A method that lets an AI look up information from a chosen source before composing an answer, rather than relying only on learned patterns.
AI Agent
A system that can use tools to carry out multi-step tasks, rather than only answering a single prompt.
Multimodal Model
A model that can work across more than one type of input, such as text, images, audio, or video.
Diffusion Model
A type of generative model often used for images that learns to turn noise into a coherent image step by step.
Mixture of Experts (MoE)
An architecture that routes a task to a subset of specialized parts of a model instead of activating the entire model every time.