Sammenlign metoder

	Variational Autoencoder	Diffusionsmodel	Principal Component Analysis
Fagområde	Dyb læring	Dyb læring	Maskinlæring
Familie	Machine learning	Machine learning	Machine learning
Oprindelsesår	2014	2020	2002
Ophavsperson	Kingma, D. P. & Welling, M.	Ho, J., Jain, A. & Abbeel, P.	Jolliffe, I.T. (textbook); Pearson & Hotelling (origins)
Type	Deep generative latent-variable model (encoder–decoder)	Generative deep learning (denoising diffusion)	Unsupervised dimensionality reduction
Oprindelig kilde	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).	Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS.	Jolliffe, I.T. (2002). Principal Component Analysis (2nd ed.). Springer.
Aliasser	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model	Difüzyon Modeli (DDPM / Stable Diffusion), difüzyon modeli, denoising diffusion model, DDPM	Temel Bileşenler Analizi (PCA), PCA, principal components analysis, Karhunen-Loève transform
Relaterede	5	4	3
Resumé	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.	A diffusion model is a generative deep-learning method, introduced by Ho, Jain and Abbeel in 2020 (DDPM), that learns to produce high-quality images, audio and molecular structures by reversing a step-by-step noising process. It has largely displaced GANs as the current state of the art in generative modelling.	Principal Component Analysis (PCA) is an unsupervised dimensionality-reduction method — given its modern textbook treatment by Ian Jolliffe (2002) — that compresses high-dimensional data into fewer dimensions while preserving the maximum possible variance. It re-expresses correlated variables as a small set of uncorrelated principal components ordered by how much of the data's variation each one captures.