השוואת שיטות
סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.
| רשת פרספטרון רב-שכבתי (MLP) חצי-מפוקחת× | רשת רב-שכבתית מכווננת (Fine-Tuned Multilayer Perceptron)× | |
|---|---|---|
| תחום | למידה עמוקה | למידה עמוקה |
| משפחה | Machine learning | Machine learning |
| שנת המקור≠ | 2006–2013 | 1986 (MLP); fine-tuning practice formalised c. 2014 |
| הוגה השיטה≠ | Chapelle, O.; Scholkopf, B.; Zien, A. (eds.); Lee, D.-H. | Rumelhart, Hinton & Williams (MLP); Yosinski et al. (fine-tuning analysis) |
| סוג≠ | Semi-supervised feedforward neural network | Supervised deep learning with pre-trained weight initialisation |
| מקור מכונן≠ | Chapelle, O., Scholkopf, B. & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 | Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536. DOI ↗ |
| כינויים | SSL-MLP, semi-supervised MLP, semi-supervised feedforward network, partially supervised multilayer perceptron | fine-tuned MLP, adapted MLP, domain-adapted multilayer perceptron, MLP fine-tuning |
| קשורות | 4 | 4 |
| תקציר≠ | A semi-supervised multilayer perceptron (SSL-MLP) is a feedforward neural network trained on a small pool of labeled examples together with a larger pool of unlabeled examples. By combining supervised cross-entropy loss on labeled data with an unsupervised consistency or pseudo-label objective on unlabeled data, it extracts far more signal from the data than a purely supervised MLP trained on labels alone. | 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. |
| ScholarGateמערך נתונים ↗ |
|
|