পদ্ধতির তুলনা করুন

	অটোএনকোডার	Locally Linear Embedding (LLE)	সাপোর্ট ভেক্টর মেশিন (শ্রেণীকরণ)
ক্ষেত্র	গভীর শিখন	যন্ত্র শিখন	যন্ত্র শিখন
পরিবার	Machine learning	Machine learning	Machine learning
উদ্ভবের বছর	2006	2000	1995
প্রবর্তক	Hinton, G.E. & Salakhutdinov, R.R.	Sam Roweis & Lawrence Saul	Cortes, C. & Vapnik, V.
ধরন	Neural network (encoder-decoder)	Nonlinear manifold dimensionality reduction	Maximum-margin classifier (kernel method)
মৌলিক উৎস	Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Roweis, S. T., & Saul, L. K. (2000). Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500), 2323–2326.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
অপর নাম	Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network	LLE, manifold learning, nonlinear dimensionality reduction, yerel doğrusal gömme	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
সম্পর্কিত	4	3	5
সারসংক্ষেপ	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.	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.	The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data.