Krahasoni metodat

	LoRA dhe PEFT	Autoenkoderi Varioacional	Vision Transformer
Fusha	Mësimi i thellë	Mësimi i thellë	Mësimi i thellë
Familja	Machine learning	Machine learning	Machine learning
Viti i origjinës	2022	2014	2021
Krijuesi	Hu, E. J. et al.; Lester, B. et al.	Kingma, D. P. & Welling, M.	Dosovitskiy, A. et al.
Lloji	Parameter-efficient fine-tuning of large pretrained models	Deep generative latent-variable model (encoder–decoder)	Transformer architecture for images (self-attention over patches)
Burimi themelues	Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR.	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.
Emërtime të tjera	LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Të lidhura	5	5	5
Përmbledhja	LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched.	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).