model

Machine learning

A parameterized function, together with the learned values of its parametersparameter, n.: One of the adjustable numbers inside an AI model that are tuned during training. Large language models have billions of them, and together they store what the model has learned., that maps inputs to outputs: for example a decision treedecision tree, n.: A model that makes a prediction by asking a series of yes-or-no questions about the input, like a flowchart, with each answer leading to the next question until it reaches a final answer., a logistic regressionlogistic regression, n.: A simple, widely used method for yes-or-no predictions that outputs a probability — say, a 70% chance a customer cancels — by passing a weighted sum of inputs through an S-shaped curve. or a neural networkneural network, n.: A kind of computer program that learns a task from examples by tuning thousands to billions of connections between simple number-crunching units, an arrangement loosely inspired by nerve cells in the brain.. A model is specified by its architecture or hypothesis class and fixed by trainingtraining, n.: The process by which an AI model learns: it is shown huge numbers of examples and its internal settings are adjusted, bit by bit, until its answers get better. on data; applying it to new inputs is inferenceinference, n.: Drawing a conclusion from evidence. In today's AI it most often means running an already-trained model to get an answer, as opposed to training it.. Models are often classed by what they represent, as in generativegenerative model, n.: A model that learns what a kind of data looks like — faces, sentences, songs — well enough to produce new examples that resemble the originals without copying them. versus discriminativediscriminative model, n.: A model that learns only to tell things apart — spam or not spam, cat or dog — without learning how to produce new examples of those things. models or language modelslanguage model, n.: A system that has learned how likely different sequences of words are, so it can predict the next word in a text and, by doing that repeatedly, write text of its own.. In the language-model era the word frequently names a specific trained artifact ('the model', a checkpoint) as opposed to the software around it; see AI modelAI model, n.: The trained core of an AI: a large file of learned numbers plus the recipe for using them, which turns an input such as a question or a photo into an output. and harnessharness, n.: The software around an AI model that gives it instructions and tools, carries out its actions and decides when it stops. The model is the engine; the harness is the rest of the car..

The model is fine; the bug is in how the app formats its output.

Statistics

A mathematical description of how data are generated, usually a family of probability distributionsprobability distribution, n.: A complete description of how likely each possible outcome is — for a fair die, one-sixth for each face. A language model produces one of these over its whole vocabulary at every step. indexed by parameters, used to estimate quantities, test hypotheses or predict. Statisticians distinguish parametricparametric model, n.: A model whose shape is fixed in advance by a set number of adjustable settings, like a straight line's slope and intercept. More data refines those settings but never adds new ones. from nonparametricnonparametric model, n.: A model that lets the data decide how complex it becomes: the more examples it gets, the more detail it can capture — for instance, one that predicts by comparing a new case with every stored example. models and stress that every model is an idealization judged by its usefulness.

Science and engineering

A simplified representation of a real system, whether physical, mathematical or computational, used to explain or predict its behavior, as in climate models or models of cognition. In AI the related idea of a world modelworld model, n.: An AI's internal simulation of how its world works, which lets it predict what will happen next — especially in response to its own actions — and so plan, imagine or practice without acting for real. is an agent's internal representation of how its environment works.

Logic

In first-order logicfirst-order logic, n.: A precise formal language for statements about objects and their relations, using 'for all' and 'there exists', such as 'every person has a mother'. It is the standard logic of mathematics and of classic AI. and model theory, an interpretation (a domain of objects plus meanings for the symbols) under which a given set of sentences comes out true. Automated reasoning and SAT solversBoolean satisfiability problem, n.: The puzzle of deciding whether a set of true-or-false conditions can all be met at once. It is famously hard in theory, yet modern solvers routinely handle millions of conditions. search for models of formulas or prove that none exist.