Methoden vergleichen

	Feinabgestimmter Mehrschichten-Perzeptron	Feinabgestimmtes Convolutional Neural Network
Fachgebiet	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning
Entstehungsjahr	1986 (MLP); fine-tuning practice formalised c. 2014	2012–2014
Urheber	Rumelhart, Hinton & Williams (MLP); Yosinski et al. (fine-tuning analysis)	Yosinski, J. et al. (theoretical basis); practice widespread from Krizhevsky et al. 2012 onward
Typ	Supervised deep learning with pre-trained weight initialisation	Transfer learning technique (supervised fine-tuning)
Wegweisende Quelle	Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.	Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27.
Aliasnamen	fine-tuned MLP, adapted MLP, domain-adapted multilayer perceptron, MLP fine-tuning	Fine-tuned CNN, CNN fine-tuning, CNN transfer learning with fine-tuning, adapted convolutional network
Verwandt	4	5
Zusammenfassung	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 CNN means starting from a network already trained on a large dataset — typically ImageNet — and continuing training on a smaller target dataset so the model adapts its learned visual features to a new task. This approach dramatically reduces the data and compute required to reach strong performance compared with training from scratch.