So sánh phương pháp

	Bộ tự mã hóa	Phân cụm K-means	Bộ tự mã hóa biến phân
Lĩnh vực	Học sâu	Học máy	Học sâu
Họ	Machine learning	Machine learning	Machine learning
Năm ra đời	2006	1967 (formalized 1982)	2014
Người khởi xướng	Hinton, G.E. & Salakhutdinov, R.R.	MacQueen, J. B.; Lloyd, S. P.	Kingma, D. P. & Welling, M.
Loại	Neural network (encoder-decoder)	Partitional clustering	Deep generative latent-variable model (encoder–decoder)
Công trình gốc	Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Lloyd, S. P. (1982). Least squares quantization in PCM. IEEE Transactions on Information Theory, 28(2), 129–137.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
Tên gọi khác	Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network	k-means clustering, Lloyd's algorithm, k-means partitioning, hard k-means	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
Liên quan	4	4	5
Tóm tắt	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.	K-means is a classic unsupervised partitional clustering algorithm that divides a dataset into K non-overlapping groups by iteratively assigning each observation to its nearest centroid and updating centroids as the mean of their assigned points. It is one of the most widely used exploratory tools in machine learning and data analysis.	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.