Linganisha mbinu

	Multilayer Perceptron Iliyoendeshwa Vizuri	Transformer Iliyoboreshwa
Nyanja	Ujifunzaji wa Kina	Ujifunzaji wa Kina
Familia	Machine learning	Machine learning
Mwaka wa asili	1986 (MLP); fine-tuning practice formalised c. 2014	2017–2019
Mwanzilishi	Rumelhart, Hinton & Williams (MLP); Yosinski et al. (fine-tuning analysis)	Vaswani et al. (architecture); fine-tuning paradigm popularised by Howard & Ruder, Devlin et al.
Aina	Supervised deep learning with pre-trained weight initialisation	Transfer learning / supervised fine-tuning
Chanzo asilia	Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.	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.
Majina mbadala	fine-tuned MLP, adapted MLP, domain-adapted multilayer perceptron, MLP fine-tuning	Transformer fine-tuning, pre-trained transformer fine-tuning, task-adaptive transformer, downstream-tuned transformer
Zinazohusiana	4	4
Muhtasari	A Fine-Tuned Multilayer Perceptron starts from weights learned on a source task — or a large general-purpose dataset — and continues training on a smaller target dataset with a reduced learning rate. This reuse of pre-learned representations allows the MLP to converge faster and generalise better than training from scratch, especially when labelled 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.