Módszerek összehasonlítása

	Finomhangolt Variációs Autoenkóder	Finomhangolt Transformer
Tudományterület	Mélytanulás	Mélytanulás
Módszercsalád	Machine learning	Machine learning
Keletkezés éve	2014 (VAE); fine-tuning practice from 2015 onward	2017–2019
Megalkotó	Kingma, D. P. & Welling, M. (VAE); fine-tuning strategy from transfer learning literature	Vaswani et al. (architecture); fine-tuning paradigm popularised by Howard & Ruder, Devlin et al.
Típus	Generative model with fine-tuning	Transfer learning / supervised fine-tuning
Alapmű	Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014).	Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
Alternatív nevek	fine-tuned VAE, domain-adapted VAE, transfer-learned VAE, adapted variational autoencoder	Transformer fine-tuning, pre-trained transformer fine-tuning, task-adaptive transformer, downstream-tuned transformer
Kapcsolódó	6	4
Összefoglaló	A Fine-Tuned Variational Autoencoder begins with a VAE pre-trained on a large source dataset and then continues training on a smaller target-domain dataset. This approach adapts the learned latent representation and generative capacity to new data, preserving general structure while specializing to the target distribution — yielding better results than training from scratch when labeled or large target data is scarce.	Fine-tuning a Transformer adapts a large pre-trained model — such as BERT, GPT, or ViT — to a specific downstream task by continuing gradient-based training on a labelled target dataset. This two-stage paradigm (pre-train then fine-tune) consistently achieves state-of-the-art results across NLP and computer vision tasks with far less task-specific data than training from scratch.