방법 비교

	오토인코더	Isomap	국소 선형 임베딩 (LLE)
분야	딥러닝	머신러닝	머신러닝
계열	Machine learning	Latent structure	Machine learning
기원 연도	2006	2000	2000
창시자	Hinton, G.E. & Salakhutdinov, R.R.	Tenenbaum, J. B.; de Silva, V.; Langford, J. C.	Sam Roweis & Lawrence Saul
유형	Neural network (encoder-decoder)	Manifold learning / nonlinear dimensionality reduction	Nonlinear manifold dimensionality reduction
원전	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.
별칭	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
관련	4	3	3
요약	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.