Manifold regularization (original) (raw)
In machine learning, Manifold regularization is a technique for using the shape of a dataset to constrain the functions that should be learned on that dataset. In many machine learning problems, the data to be learned do not cover the entire input space. For example, a facial recognition system may not need to classify any possible image, but only the subset of images that contain faces. The technique of manifold learning assumes that the relevant subset of data comes from a manifold, a mathematical structure with useful properties. The technique also assumes that the function to be learned is smooth: data with different labels are not likely to be close together, and so the labeling function should not change quickly in areas where there are likely to be many data points. Because of this
| Property | Value |
|---|---|
| dbo:abstract | In machine learning, Manifold regularization is a technique for using the shape of a dataset to constrain the functions that should be learned on that dataset. In many machine learning problems, the data to be learned do not cover the entire input space. For example, a facial recognition system may not need to classify any possible image, but only the subset of images that contain faces. The technique of manifold learning assumes that the relevant subset of data comes from a manifold, a mathematical structure with useful properties. The technique also assumes that the function to be learned is smooth: data with different labels are not likely to be close together, and so the labeling function should not change quickly in areas where there are likely to be many data points. Because of this assumption, a manifold regularization algorithm can use unlabeled data to inform where the learned function is allowed to change quickly and where it is not, using an extension of the technique of Tikhonov regularization. Manifold regularization algorithms can extend supervised learning algorithms in semi-supervised learning and transductive learning settings, where unlabeled data are available. The technique has been used for applications including medical imaging, geographical imaging, and object recognition. (en) |
| dbo:thumbnail | wiki-commons:Special:FilePath/Example_of_unlabeled_...semisupervised_learning.png?width=300 |
| dbo:wikiPageExternalLink | http://manifold.cs.uchicago.edu/manifold_regularization/software.html http://www.dii.unisi.it/~melacci/lapsvmp/ http://dlib.net/ml.html |
| dbo:wikiPageID | 48777199 (xsd:integer) |
| dbo:wikiPageLength | 28029 (xsd:nonNegativeInteger) |
| dbo:wikiPageRevisionID | 1097471695 (xsd:integer) |
| dbo:wikiPageWikiLink | dbr:Elastic_net_regularization dbr:Meshfree_methods dbr:Kernel_methods dbr:Reproducing_kernel_Hilbert_space dbr:Curse_of_dimensionality dbr:Medical_imaging dbr:Norm_(mathematics) dbr:Representer_theorem dbr:MATLAB dbr:Machine_learning dbr:Kernel_method dbc:Machine_learning dbr:C++ dbr:Document_classification dbr:Duality_(optimization) dbr:Laplacian_matrix dbr:Least_squares dbr:Spectral_graph_theory dbr:Facial_recognition_system dbr:Finite_difference_method dbr:Regression_analysis dbr:Regularization_(mathematics) dbr:Hinge_loss dbr:Hyperparameter_optimization dbr:K-nearest_neighbors_algorithm dbr:Laplace–Beltrami_operator dbr:Support_vector_machines dbr:Co-training dbr:Tikhonov_regularization dbr:Transduction_(machine_learning) dbr:Differential_geometry dbr:Divergence dbr:Manifold dbr:Spectroscopy dbr:Loss_function dbr:Mean_squared_error dbr:Semi-supervised_learning dbr:Statistical_classification dbr:Manifold_hypothesis dbr:Well-posed_problem dbr:Overfitting dbr:Manifold_learning dbr:Supervised_learning dbr:Linear_program dbr:Reproducing_kernel_Hilbert_spaces dbr:Probability_density dbr:Brain–computer_interfaces dbr:File:Example_of_unlabeled_data_in_semisupervised_learning.png dbr:File:Swissroll_manifold_unrolled.png |
| dbp:wikiPageUsesTemplate | dbt:Citation_needed dbt:Reflist |
| dct:subject | dbc:Machine_learning |
| gold:hypernym | dbr:Technique |
| rdf:type | dbo:TopicalConcept |
| rdfs:comment | In machine learning, Manifold regularization is a technique for using the shape of a dataset to constrain the functions that should be learned on that dataset. In many machine learning problems, the data to be learned do not cover the entire input space. For example, a facial recognition system may not need to classify any possible image, but only the subset of images that contain faces. The technique of manifold learning assumes that the relevant subset of data comes from a manifold, a mathematical structure with useful properties. The technique also assumes that the function to be learned is smooth: data with different labels are not likely to be close together, and so the labeling function should not change quickly in areas where there are likely to be many data points. Because of this (en) |
| rdfs:label | Manifold regularization (en) |
| owl:sameAs | wikidata:Manifold regularization https://global.dbpedia.org/id/2F9Ce |
| prov:wasDerivedFrom | wikipedia-en:Manifold_regularization?oldid=1097471695&ns=0 |
| foaf:depiction | wiki-commons:Special:FilePath/Example_of_unlabeled_data_in_semisupervised_learning.png wiki-commons:Special:FilePath/Swissroll_manifold_unrolled.png |
| foaf:isPrimaryTopicOf | wikipedia-en:Manifold_regularization |
| is dbo:wikiPageWikiLink of | dbr:Reproducing_kernel_Hilbert_space dbr:Machine_learning dbr:Manifold_hypothesis dbr:Weak_supervision dbr:Outline_of_machine_learning |
| is rdfs:seeAlso of | dbr:Nonlinear_dimensionality_reduction |
| is foaf:primaryTopic of | wikipedia-en:Manifold_regularization |
