The Complete
AI Glossary.
Every major concept in artificial intelligence, defined simply and without jargon.
Agent
An AI system that can perceive its environment, make decisions, and take actions to achieve a specific goal.
Algorithm
A set of rules or instructions given to an AI system to help it learn on its own.
Alignment
The process of ensuring AI systems are aligned with human values and do what they are intended to do without side effects.
Artificial General Intelligence (AGI)
A hypothetical type of AI that equals or exceeds human intelligence across a wide range of tasks.
Artificial Intelligence (AI)
The broader concept of machines being able to carry out tasks in a way that we would consider 'smart'.
Bias
Prejudice in favor or against one thing, person, or group compared with another, often learned from flawed training data.
Computer Vision
A field of AI that enables computers to derive meaningful information from digital images, videos, and other visual inputs.
Deep Learning
A subset of machine learning based on artificial neural networks with multiple layers (hence 'deep').
Fine-tuning
Taking a pre-trained model and continuing to train it on a smaller, specialized dataset to adapt it for a specific task.
Generative AI
A type of AI designed to create new content—like text, images, or audio—based on the patterns it has learned.
Hallucination
When a generative AI model presents false or invented information as if it were factual.
Inference
The phase where a trained AI model is put to work making predictions or generating outputs based on new, unseen data.
Large Language Model (LLM)
A type of AI model trained on massive amounts of text to understand, generate, and interact in human language.
Machine Learning (ML)
A method of data analysis that automates analytical model building, allowing systems to learn from data with minimal human intervention.
Natural Language Processing (NLP)
A branch of AI that helps computers understand, interpret, and manipulate human language.
Neural Network
A series of algorithms that endeavors to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates.
Overfitting
A modeling error that occurs when a function is too closely fit to a limited set of data points, making it perform poorly on new data.
Parameters
The variables or 'weights' inside a neural network that the model learns during training. More parameters generally mean a more capable model.
Prompt
The text input given to an AI model by a human user to tell it what to generate.
Prompt Engineering
The skill of designing and refining text prompts to get the best possible output from generative AI models.
Reinforcement Learning
A type of machine learning where an AI agent learns to behave in an environment by performing actions and seeing the results (rewards or penalties).
Supervised Learning
Training an AI model using 'labeled' data, where the model sees the input and the correct output, learning to map them together.
Token
A piece of a word. The basic building blocks that language models use to read and process text.
Transformer
A specific type of neural network architecture introduced in 2017 that revolutionized natural language processing by tracking relationships in sequential data.
Unsupervised Learning
Training an AI model using data that has no historical labels, asking the system to find its own patterns and structure.