השוואת שיטות

	LoRA ו-PEFT	יער אקראי	טרנספורמר ראייה
תחום	למידה עמוקה	למידת מכונה	למידה עמוקה
משפחה	Machine learning	Machine learning	Machine learning
שנת המקור	2022	2001	2021
הוגה השיטה	Hu, E. J. et al.; Lester, B. et al.	Breiman, L.	Dosovitskiy, A. et al.
סוג	Parameter-efficient fine-tuning of large pretrained models	Ensemble (bagging of decision trees)	Transformer architecture for images (self-attention over patches)
מקור מכונן	Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
כינויים	LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
קשורות	5	4	5
תקציר	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.	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 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).