unsupervised learning
In plain wordsMachine 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.
The machine learningmachine learning, n.: A way of building software that learns from examples instead of following rules written by a programmer. Shown thousands of labeled photos, for instance, a program can learn to recognize cats. setting in which a model learns from inputs without target labels, discovering structure in the data itself. Classic tasks are clusteringclustering, n.: Automatically sorting things into groups of similar items when nobody has said in advance what the groups should be, like sorting a drawer of odd socks into piles by color and size. (grouping similar examples, as in k-means clusteringk-means clustering, n.: A simple way to split data into a chosen number of groups: guess group centers, assign every point to its nearest center, move each center to the middle of its points, and repeat.), dimensionality reductiondimensionality reduction, n.: Squeezing data that has many measurements per item into far fewer numbers while keeping the patterns that matter, so it is easier to visualize, store or learn from. (as in principal component analysisprincipal component analysis, n.: A technique that finds the few directions in which data vary the most and describes each item by its position along them, compressing many measurements into a handful of summary scores.), density estimationdensity estimation, n.: Working out from a sample of data how likely different values are, by drawing a smooth curve or surface showing where data points bunch up and where they are rare. (modeling the probability distribution of the data) and anomaly detectionanomaly detection, n.: Automatically spotting the rare data points that don't fit the usual pattern, such as a fraudulent card payment, a machine about to fail or an intruder on a network.. Many generative modelsgenerative 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., such as autoencodersautoencoder, n.: A neural network trained to squeeze its input into a compact code and then rebuild the original from that code. Learning to compress this way forces it to capture what matters in the data. and variational autoencodersvariational autoencoder, n.: A neural network that learns to squeeze data into a compact, slightly fuzzy code and rebuild it, arranged so that decoding random codes produces new, plausible examples., are trained this way. With no targets there is no single correct answer, so evaluation relies on internal criteria, usefulness for downstream tasks or human judgment. The boundary with self-supervised learningself-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. is fuzzy: predicting masked or next tokenstoken, n.: The small chunk of text an AI language model reads and writes — often a word, part of a word or a punctuation mark. AI usage, limits and prices are counted in tokens. uses no human labels and was long called unsupervised, but it does train on targets derived from the data.
Unsupervised learning split our customers into five clusters, and marketing named them afterwards.
Origin
Contrasted with learning 'with a teacher' in 1960s pattern-recognition research; Richard Duda and Peter Hart's textbook Pattern Classification and Scene Analysis (1973) treated unsupervised learning together with clustering. Neural-network work of the 1980s (competitive learning, self-organizing maps) and Geoffrey Hinton and Terrence Sejnowski's edited volume Unsupervised Learning (1999) consolidated the term.
Usage note
Early papers on language-model pretraining, such as GPT-2's 'Language Models are Unsupervised Multitask Learners' (2019), called it unsupervised; since about 2019 the more precise term self-supervised has prevailed.
Related
- clusteringclustering, n.: Automatically sorting things into groups of similar items when nobody has said in advance what the groups should be, like sorting a drawer of odd socks into piles by color and size.
- dimensionality reductiondimensionality reduction, n.: Squeezing data that has many measurements per item into far fewer numbers while keeping the patterns that matter, so it is easier to visualize, store or learn from.
- density estimationdensity estimation, n.: Working out from a sample of data how likely different values are, by drawing a smooth curve or surface showing where data points bunch up and where they are rare.
- self-supervised learningself-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.
- autoencoderautoencoder, n.: A neural network trained to squeeze its input into a compact code and then rebuild the original from that code. Learning to compress this way forces it to capture what matters in the data.
- anomaly detectionanomaly detection, n.: Automatically spotting the rare data points that don't fit the usual pattern, such as a fraudulent card payment, a machine about to fail or an intruder on a network.
- generative modelgenerative 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.
- supervised learningsupervised 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.
Mentioned in
machine learningmachine learning, n.: A way of building software that learns from examples instead of following rules written by a programmer. Shown thousands of labeled photos, for instance, a program can learn to recognize cats., reinforcement learningreinforcement 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., association rule learningassociation rule learning, n.: Finding 'if this, then often that' patterns in large records of transactions, such as noticing that shoppers who buy pasta and tomatoes often buy parmesan too., clusteringclustering, n.: Automatically sorting things into groups of similar items when nobody has said in advance what the groups should be, like sorting a drawer of odd socks into piles by color and size., Donald HebbDonald Hebb, prop. n.: A Canadian psychologist who proposed in 1949 that connections between brain cells strengthen when the cells are active together, an idea behind many learning rules for neural networks., 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'., learninglearning, n.: Getting better at something through experience. For a machine, it means changing its internal settings based on data so that it performs a task better than before., self-supervised learningself-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-supervised learningsemi-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., supervised learningsupervised 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., self-organizing mapself-organizing map, n.: A neural network that arranges data on a flat grid so that similar items end up in neighboring cells, producing a map of how the data is organized., Teuvo KohonenTeuvo Kohonen, prop. n.: A Finnish engineer who invented the self-organizing map, a neural network that arranges complex data on a simple grid so that similar items end up next to each other.