learning

Machine learning

A change in a system, driven by data, interaction or feedback rather than by someone rewriting it, that leaves it better at some tasktask (machine learning), n.: The job an AI model is meant to do, such as translating sentences, spotting spam or answering questions, defined by its inputs, its expected outputs and how success is scored.. In most current AI, learning means adjusting a model'smodel, n.: A simplified working version of something. In AI it usually means the trained program, a big set of learned numbers, that takes an input and produces an answer, prediction or piece of content. 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. to reduce a loss functionloss function, n.: A score that measures how wrong a model's predictions are. Training means adjusting the model, step by step, to push this number down. or increase a rewardreward, n.: The score an AI system receives after an action, telling it how good the outcome was. Reinforcement learning trains the system to collect as much reward as possible over time.. It is classified by the kind of feedback (supervisedsupervised learning, n.: Teaching a computer by example: you give it many inputs paired with the right answers, such as photos labeled 'cat' or 'dog', and it learns to answer correctly for new inputs., unsupervisedunsupervised learning, n.: Machine learning without answer keys: the computer looks at unlabeled data and finds structure on its own, such as groups of similar customers or the main ways in which data vary., self-supervisedself-supervised learning, n.: A way for AI to learn from huge amounts of unlabeled data by setting itself fill-in-the-blank puzzles, such as guessing a hidden word or a missing patch of an image., semi-supervisedsemi-supervised learning, n.: Machine learning that combines a small set of labeled examples with a much larger pile of unlabeled ones, which are cheaper to collect, to learn better than from the labeled data alone., reinforcementreinforcement learning, n.: A way of teaching a computer program by trial and error: it tries actions, earns points for good results and penalties for bad ones, and gradually learns which choices pay off over time.), by when it happens (onlineonline learning, n.: Learning from data that arrive one piece at a time, updating the model after each new example instead of training once on a fixed collection, as a spam filter does while emails stream in. or batch, continualcontinual learning, n.: The ability of an AI to keep learning new things over time from a stream of experience, without forgetting what it already knew and without being retrained from scratch.) and by what carries over (transfertransfer learning, n.: Reusing what a model learned on one task to get a head start on another — like a pianist picking up the organ faster than a beginner. It lets models learn new jobs from little data., meta-learningmeta-learning, n.: Training a system across many different tasks so that it gets better at learning itself, letting it pick up a new task quickly from only a few examples.). Learning theory, from PAC learningPAC learning, n.: A mathematical definition of what it means to learn from examples: given enough data, a learner should, with high probability, find a rule that is almost always right. to VC dimensionVC dimension, n.: A measure of how flexible a family of prediction rules is: the largest number of points it can label in every possible way. More flexible families need more data to learn reliably. bounds, asks how much data a learner needs to generalize.

Most of the learning happens in pretraining; fine-tuning mainly changes how the model presents what it knows.

In-context

By extension, adaptation without any parameter change, as in in-context learningin-context learning, n.: A language model's ability to pick up a new task from instructions or examples placed in its input, on the spot, without any retraining — like a quick study learning a game's rules from one round., where a large language modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. picks up a task from examples or instructions in its prompt. Whether this counts as learning in the classical sense is debated; the adaptation disappears when the context is cleared.

Psychology and neuroscience

The process by which experience leaves durable marks on what an animal or person knows or does, studied through conditioning, memory and skill acquisition. Ideas from this tradition, such as Hebbian learningHebbian learning, n.: The idea that a connection between two brain cells grows stronger when they are active at the same time — the principle behind the slogan 'cells that fire together wire together'. and reward prediction errors, inspired machine-learning methods, and machine-learning models are in turn used as theories of animal and human learning.