AI Mastery / GlossaryAI Glossary 75 words you will meet when you learn AI, each explained in plain English with an everyday example. Every term has its own page. Start with the basics, or jump to a section.
The basics How machines learn Neural networks Language models & chatbots Data Generative AI & the senses Safety & ethics Everyday AI New to all of this? Start the AI Basics course → The basics Algorithm An algorithm is a precise, step-by-step set of instructions that a computer follows to solve a problem or complete a task. API An API (application programming interface) is a set of rules that lets one program ask another for data or actions, such as sending a question to an AI model. Artificial general intelligence Artificial general intelligence (AGI) is a hypothetical AI that could learn and perform any intellectual task a human can, rather than only specific tasks. Artificial intelligence Artificial intelligence (AI) is software that does tasks that usually need human thinking, like recognizing faces, understanding speech, or making decisions. Chatbot A chatbot is a computer program that holds a conversation with people through text or voice, ranging from simple scripted menus to AI assistants. Deep learning Deep learning is machine learning that uses neural networks with many layers, so a computer can learn very complex patterns from huge amounts of data. Generative AI Generative AI is artificial intelligence that creates new content, such as text, images, music, code, or video, from patterns it learned in existing examples. Inference Inference is the stage where a trained AI model is actually used: it takes a new input and produces a prediction or an answer. Machine learning Machine learning is a way of building software where the computer learns patterns from examples, instead of a programmer writing every rule by hand. Model In AI, a model is the trained program that has learned patterns from data and can now make predictions or generate output for new inputs. Training Training is the process of teaching an AI model by showing it many examples and adjusting its internal numbers until its answers become accurate. Turing test The Turing test is a 1950 thought experiment by Alan Turing: if a person chatting by text cannot tell a machine from a human, the machine passes. How machines learn Accuracy Accuracy is the share of a model's predictions that are correct, calculated as the number it got right divided by the total number it tried. Backpropagation Backpropagation is the algorithm that works out how much each weight in a neural network contributed to an error, so every weight can be adjusted correctly. Benchmark A benchmark is a standard set of test tasks used to measure and compare AI models, so different systems can be scored on exactly the same questions. Classification Classification is a machine learning task where the model sorts each input into one of a fixed set of categories, such as spam or not spam. Clustering Clustering is an unsupervised learning method that groups similar data points together automatically, without being told in advance what the groups are. False positive A false positive is a mistake where a model says 'yes' when the true answer is 'no', like flagging a safe email as spam or a healthy patient as sick. Gradient descent Gradient descent is the step-by-step method used to train models: it repeatedly adjusts the model's numbers in the direction that most reduces its error. Loss function A loss function is the score that measures how wrong a model's predictions are; training adjusts the model to make that score as small as possible. Overfitting Overfitting is when a model memorizes its training examples, including noise and quirks, so it performs well on them but poorly on new, unseen data. Regression Regression is a machine learning task where the model predicts a number, such as a price, a temperature, or a delivery time, rather than a category. Reinforcement learning Reinforcement learning is machine learning where a program learns by trial and error, receiving rewards for good actions and penalties for bad ones. Supervised learning Supervised learning is machine learning where the model trains on examples that come with the correct answers, so it can learn to predict answers for new data. Threshold A threshold is the cutoff score a model's confidence must reach before it counts as a 'yes'; moving it trades fewer false alarms for more missed cases. Unsupervised learning Unsupervised learning is machine learning on data that has no labels, where the model must find structure, groups, or patterns on its own. Language models & chatbots AI agent An AI agent is a system that uses a language model to plan and carry out multi-step tasks on its own, deciding which actions and tools to use along the way. ChatGPT ChatGPT is OpenAI's chatbot, released in November 2022, that lets people talk to a large language model; GPT stands for Generative Pre-trained Transformer. Context window The context window is the maximum amount of text, measured in tokens, that a language model can consider at once, including your prompt and its own reply. Embedding An embedding is a list of numbers that represents the meaning of a piece of text, image, or other data, arranged so similar meanings produce similar numbers. Fine-tuning Fine-tuning is taking an already-trained model and training it a bit more on a smaller, specific set of examples so it performs better at a particular job. Hallucination An AI hallucination is when a language model states something false or invented as if it were a fact, such as a fake quote, citation, or event. Large language model A large language model (LLM) is an AI trained on vast amounts of text to predict the next word, which lets it write, answer questions, summarize, and converse. Open weights An open-weights model is one whose trained parameters have been published, so anyone can download it, run it on their own hardware, and modify it. Pretraining Pretraining is the first and biggest stage of building a language model, where it learns general language and knowledge by predicting text across huge datasets. Prompt A prompt is the text you give an AI model to tell it what you want; it can be a question, an instruction, an example, or a whole document to work with. Prompt engineering Prompt engineering is the practice of writing and refining prompts so that an AI model gives more accurate, useful, and consistent results. RAG RAG (retrieval-augmented generation) is a technique where an AI looks up relevant documents first, then uses them to write an answer grounded in real sources. RLHF RLHF is a training step where human raters compare a model's answers and the model is then adjusted to produce the kind of replies people prefer. Semantic search Semantic search is search that finds results by meaning rather than exact keywords, so a query and a document can match even when they share no words. System prompt A system prompt is hidden instruction text set by the app developer that tells an AI model how to behave, before the user's own message is added. Temperature Temperature is a setting that controls how random a language model's replies are: low values give focused, predictable text; high values give more variety. Token A token is the unit of text a language model reads and writes; it is usually a word, part of a word, or a punctuation mark, roughly four characters in English. Tool calling Tool calling lets a language model request that an outside program run, such as a calculator, database, or web search, and then use the result in its answer. Vector A vector is an ordered list of numbers; in AI it is how meaning, images, and other data are represented so computers can compare and calculate with them. Vector database A vector database is a storage system built to hold embeddings and quickly find the ones most similar to a query, which powers search by meaning. Data Bias (in AI) AI bias is when a model gives systematically unfair or skewed results for some groups, usually because its training data reflected real-world prejudice or gaps. Dataset A dataset is an organized collection of data, such as images, text, or records, gathered for a purpose like training or testing an AI model. Features Features are the individual measurable properties of an example that a model uses as input, such as a house's size, age, and location when predicting its price. Label A label is the correct answer attached to a training example, such as the tag 'cat' on a photo, that a supervised model learns to predict. Training data Training data is the collection of examples an AI model learns from; the patterns in that data determine what the model can do and the mistakes it will make. Generative AI & the senses Computer vision Computer vision is the field of AI that lets computers understand images and video, including recognizing objects, faces, text, and movement. Diffusion model A diffusion model is a generative AI that creates images or other data by starting from random noise and removing it step by step until a clear result appears. GAN A GAN (generative adversarial network) is a pair of neural networks that train by competing: one creates fake examples and the other tries to spot the fakes. Image generation Image generation is the use of AI to create new pictures from a description, a sketch, or another image, rather than retrieving photos that already exist. Multimodal AI Multimodal AI is a model that can take in and combine several kinds of input, such as text, images, audio, and video, and often produce several kinds too. Natural language processing Natural language processing (NLP) is the branch of AI focused on letting computers read, understand, and produce human language like English or Hindi. Speech recognition Speech recognition is the technology that converts spoken words into written text, powering dictation, voice assistants, and automatic captions. Safety & ethics AI ethics AI ethics is the study of how AI should be built and used so that it is fair, transparent, respects privacy, and benefits people rather than harming them. AI safety AI safety is the field devoted to making AI systems behave reliably, avoid causing harm, and remain under meaningful human control as they grow more capable. Alignment Alignment is the challenge of making an AI system's goals and behavior match what people actually intend, rather than only what they literally asked for. Deepfake A deepfake is a fake image, video, or audio clip made with AI that shows a real person doing or saying something they never did, often convincingly. Explainability Explainability is the ability to understand and describe why an AI model produced a particular output, instead of treating it as an unexplained black box. Guardrails Guardrails are rules and checks placed around an AI system to keep its behavior within safe limits, such as blocking harmful requests or unsafe replies. Jailbreak A jailbreak is a trick that gets an AI model to ignore its safety rules and produce content it was designed to refuse, usually through a cleverly worded prompt.