AI Dictionary

Core Concepts

Glossary of AI concepts, explained simply

42 concepts

Core Concepts

42 concepts

Illustration: a baker kneading a large lump of dough while a hand adds a spoonful of an ingredient

Intermediate

Core Concepts

Batch size and learning rate

Batch size and learning rate are two settings for training an AI model: how many examples it sees before each adjustment, and how big each adjustment is.

Illustration: an old craftsman adding fine detail to an ornate carved panel, next to a small robot with simple cut-out flowers

Intermediate

Core Concepts

Overfitting and underfitting

Overfitting means an AI model has learned its examples by heart and fails on new cases; underfitting means it is too simple to learn the pattern at all.

Illustration: a robot with a magnifying glass studying a small wooden pyramid in front of shelves of stacked jars

Advanced

Core Concepts

Scaling laws for LLMs

Scaling laws are formulas from experiments that predict how much better an AI language model gets with more parameters, more training data or more computing power.

Illustration: an owl with glasses reading an open book, with rolled scrolls beside it and a mouse following a trail of glowing coins

Beginner

Core Concepts

AI inference

Inference is the moment a trained AI model does its work: it takes your question, text or photo and turns it into an answer, as in every chatbot reply.

Illustration: shelves of coloured jars with a walking magnifying glass and small figures in hats

Beginner

Core Concepts

Classifier

A classifier is an AI model that sorts each input into one of a set of categories you chose, such as spam or not spam, or which team a ticket goes to.

Illustration: an owl on a ladder with a basket of glowing cards while squirrels fetch books from the shelves

Beginner

Core Concepts

Context window

A context window is how much text an AI model can take in at once, from your question and documents to its own answer, counted in tokens.

Illustration: a purple typewriter trailing a green ribbon in a library full of smiling book-like figures

Beginner

Core Concepts

Large language model (LLM)

A large language model (LLM) is the kind of AI behind chatbots such as ChatGPT: it has learned from huge amounts of text to understand questions and write answers.

Illustration: a patchwork tailor's dummy with a yellow measuring tape in a sewing workshop

Intermediate

Core Concepts

Loss function

A loss function is the score that tells an AI model during training how wrong its answers are, so that training can adjust the model to make fewer mistakes.

Illustration: a branching wooden tree with gears at its joints, like a network of connected nodes

Beginner

Core Concepts

Neural network

A neural network is a computer model that learns from examples by adjusting many small connections; it is the basis of speech recognition and chatbots.

Illustration: an owl with a glowing light bulb above its head, at a desk covered in written scrolls

Beginner

Core Concepts

Prompt

A prompt is the message you give an AI model such as ChatGPT, for example a question or an instruction; the clearer you are, the more useful the answer.

Illustration: jars with smiling labels on kitchen shelves, with a whisk, a rolling pin and a chalkboard full of scribbles

Beginner

Core Concepts

Token in AI

A token is a small piece of text, such as a short word or part of a word, that an AI model reads and writes; AI services count and bill usage in tokens.

Illustration: a craftsman in an apron laying out coloured mosaic pieces on a table, with jars of pieces and puzzle shapes on the wall

Intermediate

Core Concepts

Tokenizer

A tokenizer is the part of an AI system that cuts text into tokens, the small pieces a language model works with, and turns them into numbers and back again.

Illustration: small robots with clipboards around a scoreboard, three rubber ducks on a shelf behind them

Beginner

Core Concepts

AI benchmark

An AI benchmark is a standard test with fixed questions and known answers, used to score different AI models the same way so you can compare them.

Illustration: an open book releasing coloured smoke and question marks

Beginner

Core Concepts

AI hallucination

An AI hallucination is an answer from a chatbot or other AI tool that sounds certain but is wrong or made up, such as a source that does not exist.

Illustration: glowing orange spheres floating between library bookshelves

Intermediate

Core Concepts

Embedding

An embedding is a list of numbers that captures the meaning of a text, so software can find texts that mean the same thing even when they use different words.

Illustration: a cat in glasses at a desk with books, pattern cards and a small robot

Beginner

Core Concepts

Artificial intelligence (AI)

Artificial intelligence (AI) is software that does work which normally takes human thinking, such as answering a customer's question or spotting an unusual payment.

Illustration: an old man in a workshop inspecting a toy train with a torch, a glowing brain outline behind him

Intermediate

Core Concepts

Backpropagation

Backpropagation is the calculation that lets an AI model learn from its mistakes, by working out how much each internal setting contributed to an error.

Illustration: a potter holding a jug while pots fall from the shelf behind him

Intermediate

Core Concepts

Catastrophic forgetting

Catastrophic forgetting is when an AI model loses skills it already had because it was trained further on something new, such as a company's own data.

Illustration: a robot chef stirring a pot between growing piles of paper notes

Beginner

Core Concepts

Context rot

Context rot is the decline in an AI model's work as its conversation or task grows longer, so that it starts to overlook instructions and facts from earlier on.

Illustration: clocks, gears and books on workshop shelves

Advanced

Core Concepts

Continual learning

Continual learning lets an AI model keep learning from new information after its first training, without forgetting what it learned before.

Illustration: two stacks of books with a glowing angle between them

Intermediate

Core Concepts

Cosine similarity

Cosine similarity is a score between -1 and 1 that says how alike two texts are, once an AI model has turned them into lists of numbers.

Illustration: a sewing machine stitching a glowing pattern in front of bookshelves

Beginner

Core Concepts

Deep learning

Deep learning is a form of AI that learns tasks from many examples with a many-layered neural network, such as understanding speech or recognising products in photos.

Illustration: a craftsman arranging coloured tiles on a workbench

Intermediate

Core Concepts

Feature engineering

Feature engineering is turning raw data, such as till receipts or customer records, into useful numbers, so that a prediction model can find patterns in it.

Illustration: three toasters sending puffs of steam towards one bowl

Advanced

Core Concepts

Federated learning

With federated learning, phones, shops or hospitals train one AI model together while each keeps its own data and shares only updates to the model.

Illustration: a craftsman shaping a colourful head sculpture in a workshop

Intermediate

Core Concepts

Fine-tuning

Fine-tuning is training an existing AI model further on your own examples, so that it handles a set task or writing style better than instructions alone can.

Illustration: a cat painting shapes on a canvas beside an old printing press that prints patterned paper

Beginner

Core Concepts

Generative AI

Generative AI is software that creates new content on request, such as a customer email, a product text or an image, from an instruction in plain language.

Illustration: a chef stirring a large bowl in a kitchen, surrounded by bowls of ingredients

Intermediate

Core Concepts

Gradient descent

Gradient descent is the method that trains most AI models: it adjusts the model's settings in small steps, each time in the direction that reduces its errors.

Illustration: a framed board of colourful puzzle-like shapes on a workbench, with a magnifying glass over one of them

Intermediate

Core Concepts

Latent space

Latent space is the internal map in which an AI model stores what it has learned about its input as numbers, with similar things placed close together.

Illustration: a robot with a light bulb above its head stirring a cooking pot, with jars of ingredients on shelves

Beginner

Core Concepts

Machine learning (ML)

Machine learning is software that learns from examples instead of fixed rules, such as a spam filter that learned from thousands of emails what spam looks like.

Illustration: a chef stirring a steaming pot, with question marks rising from the steam

Beginner

Core Concepts

Natural language processing (NLP)

Natural language processing (NLP) is the part of AI that lets computers read, sort, translate and write human language, as in chatbots and translation apps.

Illustration: a weaver setting up a small wooden loom in front of shelves full of wool

Intermediate

Core Concepts

Pre-training

Pre-training is the first and largest stage in training an AI model: it learns language and general knowledge from huge amounts of text, before it is adapted to tasks.

Illustration: a robot on a library ladder studying a large open book full of shapes

Intermediate

Core Concepts

Reasoning in AI

Reasoning in AI means a model works through a problem step by step before it answers, which helps with hard questions and makes answers slower and more expensive.

Illustration: a small robot at a board with tools, gold stars and smiley faces, next to shelves of jars

Intermediate

Core Concepts

Reinforcement learning (RL)

Reinforcement learning trains AI by trial and error: the system tries actions, gets a reward or a penalty for the result, and learns which choices pay off.

Illustration: a robot with a magnifying glass examining orange building blocks on a table under hanging light bulbs

Intermediate

Core Concepts

Self-supervised learning

Self-supervised learning trains AI on raw data without human labels: the model hides part of the data, such as the next word, and learns to predict it.

Illustration: an owl in glasses showing picture cards to two small birds and a mouse in a workshop

Beginner

Core Concepts

Supervised learning

Supervised learning trains an AI model on examples that come with the right answer, such as emails marked spam or not spam, so that it can handle new cases itself.

Illustration: a woman at a purple machine that makes coloured balls, with jars of similar balls on the shelves

Intermediate

Core Concepts

Synthetic data

Synthetic data is realistic but made-up data generated by a computer, used when real data is scarce, costly or too sensitive, such as customer or patient records.

Illustration: a smiling slice of toast in a toaster with a control dial

Beginner

Core Concepts

Temperature in AI

Temperature is a setting that controls how much an AI model varies its answers: a low value gives predictable replies, a high value more varied ones.

Illustration: a gardener in a greenhouse between a table of different flowers and a row of tomato plants of increasing height

Beginner

Core Concepts

Difference between regression and classification

Regression lets an AI model predict a number, such as next week's sales, while classification predicts a category, such as whether an email is spam.

Illustration: an adult holding a finished patchwork quilt while a child sews a smaller one at a workbench

Beginner

Core Concepts

Difference between training and inference

Training is how an AI model learns from examples, a large job done before release; inference is every use after that, such as each answer a chatbot gives.

Illustration: a chef choosing from numbered baskets of produce on shelves, with a cat watching from a ladder

Intermediate

Core Concepts

Top-p (nucleus) sampling

Top-p sampling is a setting that makes an AI model choose each next word only from its likeliest options, so a lower value gives more predictable text.

Illustration: an owl in an apron moving gears from an old machine into a new one on a workbench

Intermediate

Core Concepts

Transfer learning

Transfer learning is reusing what an AI model learned on one task as the starting point for another, so a related task needs far fewer of your own examples.

Illustration: an elderly chef in glasses gesturing over paper bags and bowls of ingredients in a pantry full of jars, with a black cat

Beginner

Core Concepts

Unsupervised learning

Unsupervised learning is AI training on data without answers attached: the model finds groups and patterns by itself, and a person decides what they mean.