Unsupervised learning

Part of a series on
Machine learning and data mining
hide Problems Classification Clustering Regression Anomaly detection Data Cleaning AutoML Association rules Reinforcement learning Structured prediction Feature engineering Feature learning Online learning Semi-supervised learning Unsupervised learning Learning to rank Grammar induction
show Supervised learning (classification • regression) Decision trees Ensembles Bagging Boosting Random forest k-NN Linear regression Naive Bayes Artificial neural networks Logistic regression Perceptron Relevance vector machine (RVM) Support vector machine (SVM)
show Clustering BIRCH CURE Hierarchical k-means Expectation–maximization (EM) DBSCAN OPTICS Mean shift
show Dimensionality reduction Factor analysis CCA ICA LDA NMF PCA PGD t-SNE
show Structured prediction Graphical models Bayes net Conditional random field Hidden Markov
show Anomaly detection k-NN Local outlier factor
show Artificial neural network Autoencoder Cognitive computing Deep learning DeepDream Multilayer perceptron RNN LSTM GRU ESN Restricted Boltzmann machine GAN SOM Convolutional neural network U-Net Transformer Spiking neural network Memtransistor Electrochemical RAM (ECRAM)
show Reinforcement learning Q-learning SARSA Temporal difference (TD)
show Theory Bias–variance tradeoff Computational learning theory Empirical risk minimization Occam learning PAC learning Statistical learning VC theory
show Machine-learning venues NeurIPS ICML ML JMLR ArXiv:cs.LG
show Related articles Glossary of artificial intelligence List of datasets for machine-learning research Outline of machine learning
v t

Unsupervised learning is a type of machine learning in which the algorithm is not provided with any pre-assigned labels or scores for the training data.^[1][2] As a result, unsupervised learning algorithms must first self-discover any naturally occurring patterns in that training data set. Common examples include clustering, where the algorithm automatically groups its training examples into categories with similar features, and principal component analysis, where the algorithm finds ways to compress the training data set by identifying which features are most useful for discriminating between different training examples, and discarding the rest. This contrasts with supervised learning in which the training data include pre-assigned category labels (often by a human, or from the output of non-learning classification algorithm).^[3] Other intermediate levels in the supervision spectrum include reinforcement learning, where only numerical scores are available for each training example instead of detailed tags, and semi-supervised learning where only a portion of the training data have been tagged.

Advantages of unsupervised learning include a minimal workload to prepare and audit the training set, in contrast to supervised learning techniques where a considerable amount of expert human labor is required to assign and verify the initial tags, and greater freedom to identify and exploit previously undetected patterns that may not have been noticed by the "experts". This often comes at the cost of unsupervised techniques requiring a greater amount of training data and converging more slowly to acceptable performance, increased computational and storage requirements during the exploratory process, and potentially greater susceptibility to artifacts or anomalies in the training data that might be obviously irrelevant or recognized as erroneous by a human, but are assigned undue importance by the unsupervised learning algorithm.

Approaches[]

Common families of algorithms used in unsupervised learning include: (1) clustering, (2) anomaly detection, (3) neural networks (note that not all neural networks are unsupervised; they can be trained by supervised, unsupervised, semi-supervised, or reinforcement methods), and (4) latent variable models.

• Clustering methods include hierarchical clustering,^[4] k-means,^[5] mixture models, DBSCAN,^[6] and OPTICS algorithm
• Anomaly detection methods include Local Outlier Factor, and Isolation Forest
• Approaches for learning latent variable models include expectation–maximization algorithm, the method of moments, and blind signal separation techniques (principal component analysis, independent component analysis, non-negative matrix factorization, singular value decomposition)
• Neural network methods include autoencoders, deep belief networks, Hebbian learning, generative adversarial networks (GANs), and self-organizing maps

Method of moments[]

One statistical approach for unsupervised learning is the method of moments.^[7] In the method of moments, the unknown parameters of interest in the model are related to the moments of one or more random variables. These moments are empirically estimated from the available data samples and used to calculate the most likely value distributions for each parameter. The method of moments is shown to be effective in learning the parameters of latent variable models, where in addition to the observed variables available in the training and input data sets, a number of unobserved latent variables are also assumed to exist and to determine the categorization of each same. One practical example of latent variable models in machine learning is topic modeling, which is a statistical model for predicting the words (observed variables) in a document based on the topic (latent variable) of the document. The method of moments (tensor decomposition techniques) has been shown to consistently recover the parameters of a large class of latent variable models under certain assumptions.^[8]

The expectation–maximization algorithm is another practical method for learning latent variable models. However, it can get stuck in local optima, and it is not guaranteed to converge to the true unknown parameters of the model. In contrast, using the method of moments, global convergence is guaranteed under some conditions.^[8]

Neural networks[]

The classical example of unsupervised learning in the study of neural networks is Donald Hebb's principle that "neurons that fire together wire together".^[9] In Hebbian learning, the connection is reinforced irrespective of an error, but is exclusively a function of the coincidence between action potentials between the two neurons.^[10] A similar version that modifies synaptic weights takes into account the time between the action potentials (spike-timing-dependent plasticity or STDP). Hebbian Learning has been hypothesized to underlie a range of cognitive functions, such as pattern recognition and experiential learning.

Among neural network models, the self-organizing map (SOM) and adaptive resonance theory (ART) are commonly used in unsupervised learning algorithms. The SOM is a topographic organization in which nearby locations in the map represent inputs with similar properties. The ART model allows the number of clusters to vary with problem size and lets the user control the degree of similarity between members of the same clusters by means of a user-defined constant called the vigilance parameter. ART networks are used for many pattern recognition tasks, such as automatic target recognition and seismic signal processing.^[11]

See also[]

• Automated machine learning
• Cluster analysis
• Anomaly detection
• Expectation–maximization algorithm
• Generative topographic map
• Meta-learning (computer science)
• Multivariate analysis
• Radial basis function network
• Weak supervision

References[]

Further reading[]

• Bousquet, O.; von Luxburg, U.; Raetsch, G., eds. (2004). Advanced Lectures on Machine Learning. Springer-Verlag. ISBN 978-3540231226.
• Duda, Richard O.; Hart, Peter E.; Stork, David G. (2001). "Unsupervised Learning and Clustering". Pattern classification (2nd ed.). Wiley. ISBN 0-471-05669-3.
• Hastie, Trevor; Tibshirani, Robert (2009). The Elements of Statistical Learning: Data mining, Inference, and Prediction. New York: Springer. pp. 485–586. doi:10.1007/978-0-387-84858-7_14. ISBN 978-0-387-84857-0.
• Hinton, Geoffrey; Sejnowski, Terrence J., eds. (1999). Unsupervised Learning: Foundations of Neural Computation. MIT Press. ISBN 0-262-58168-X. (This book focuses on unsupervised learning in neural networks)