Usporedite metode

	Generativna suparnička mreža	Slučajna šuma	Varijacijski autoenkoder	Vision Transformer
Područje	Duboko učenje	Strojno učenje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning	Machine learning	Machine learning
Godina nastanka	2014	2001	2014	2021
Tvorac	Goodfellow, I. et al.	Breiman, L.	Kingma, D. P. & Welling, M.	Dosovitskiy, A. et al.
Vrsta	Generative deep learning (adversarial two-network game)	Ensemble (bagging of decision trees)	Deep generative latent-variable model (encoder–decoder)	Transformer architecture for images (self-attention over patches)
Temeljni izvor	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Drugi nazivi	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Srodne	4	4	5	5
Sažetak	A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation.	Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree.	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.	The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).