Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| Mtandao wa Tabaka Nyingi Wenye Usimamizi Dhaifu× | Mtandao wa CNN wa usimamizi dhaifu× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2016–2018 | 2015–2016 |
| Mwanzilishi≠ | Multiple contributors; paradigm formalized by Zhou (2018) and Ratner et al. (2016) | Oquab, M. et al.; Zhou, B. et al. |
| Aina≠ | Feedforward neural network trained under weak supervision | Weakly supervised deep learning |
| Chanzo asilia≠ | Zhou, Z.-H. (2018). A brief introduction to weakly supervised learning. National Science Review, 5(1), 44–53. DOI ↗ | Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2921–2929. DOI ↗ |
| Majina mbadala | WS-MLP, weakly supervised feedforward network, noisy-label MLP, weak-label multilayer perceptron | WS-CNN, weakly supervised CNN, CNN with weak labels, CNN with noisy labels |
| Zinazohusiana | 5 | 5 |
| Muhtasari≠ | A Weakly Supervised Multilayer Perceptron trains a standard feedforward neural network when only imperfect supervision is available — labels may be noisy, incomplete, crowd-sourced, rule-generated, or derived from distant supervision — enabling learning at scale without the cost of full expert annotation. | A weakly supervised CNN is a convolutional neural network trained with incomplete, coarse, or noisy annotations instead of full pixel-level or bounding-box labels. Typical weak labels include image-level class tags, partial annotations, or crowd-sourced noisy labels. The model learns to classify and often to roughly localize objects using these cheaper, lower-quality supervision signals. |
| ScholarGateSeti ya data ↗ |
|
|