Сравнение методов

	Автоэнкодер	Изомап	Локально линейное вложение (LLE)
Область	Глубокое обучение	Машинное обучение	Машинное обучение
Семейство	Machine learning	Latent structure	Machine learning
Год появления	2006	2000	2000
Автор метода	Hinton, G.E. & Salakhutdinov, R.R.	Tenenbaum, J. B.; de Silva, V.; Langford, J. C.	Sam Roweis & Lawrence Saul
Тип	Neural network (encoder-decoder)	Manifold learning / nonlinear dimensionality reduction	Nonlinear manifold dimensionality reduction
Основополагающий источник	Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Tenenbaum, J. B., de Silva, V. & Langford, J. C. (2000). A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500), 2319–2323.	Roweis, S. T., & Saul, L. K. (2000). Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500), 2323–2326.
Другие названия	Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network	Isomap, isometric feature mapping, geodesic Isomap, nonlinear MDS	LLE, manifold learning, nonlinear dimensionality reduction, yerel doğrusal gömme
Связанные	4	3	3
Сводка	An autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs it, enabling dimensionality reduction and anomaly detection. By learning to rebuild its own input through a narrow bottleneck, it discovers a compact representation of the data.	Isomap (Isometric Feature Mapping) is a manifold learning algorithm introduced by Tenenbaum, de Silva, and Langford in 2000 that discovers the intrinsic low-dimensional geometry of high-dimensional data by preserving geodesic — rather than straight-line Euclidean — distances between all pairs of points. It was one of the earliest, and most influential, nonlinear dimensionality reduction methods to demonstrate that genuinely curved data manifolds could be unfolded into a faithful low-dimensional coordinate system.	Locally linear embedding, introduced by Sam Roweis and Lawrence Saul in 2000, is a manifold-learning method for nonlinear dimensionality reduction. It assumes that although data may curve through a high-dimensional space, each point and its neighbours lie approximately on a flat patch. LLE captures each point as a weighted combination of its neighbours and then finds a low-dimensional layout that preserves those same local relationships, unrolling curved structure into a faithful low-dimensional map.