Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| Mtandao wa Mawasiliano wa Nusu-Usindikaji× | Uhamishaji wa Mafunzo kwa Mitandao ya Neura ya Kimkunjo× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2013–2017 | 2010–2014 |
| Mwanzilishi≠ | Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others) | Pan, S. J. & Yang, Q. (transfer learning framework); popularized for CNNs by Yosinski et al. and Razavian et al. |
| Aina≠ | Semi-supervised deep learning | Transfer learning applied to convolutional neural networks |
| Chanzo asilia≠ | Lee, D.-H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop on Challenges in Representation Learning. link ↗ | Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ |
| Majina mbadala | SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN | TL-CNN, pretrained CNN, CNN fine-tuning, feature-extracting CNN |
| Zinazohusiana≠ | 5 | 4 |
| Muhtasari≠ | A Semi-supervised CNN trains a convolutional network on a small labeled image set and a larger pool of unlabeled images simultaneously, using techniques such as pseudo-labeling and consistency regularization to extract supervisory signal from unlabeled data. This strategy closes much of the performance gap caused by scarce annotations without requiring additional human labeling effort. | Transfer Learning with CNN reuses a convolutional neural network that has already been trained on a large dataset — most commonly ImageNet — and adapts its learned feature detectors to a new, often smaller target dataset. This lets researchers achieve strong image-recognition performance without the massive compute and data resources required to train a CNN from scratch. |
| ScholarGateSeti ya data ↗ |
|
|