方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 课程学习× | 知识蒸馏× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2009 | 2015 |
| 提出者≠ | Yoshua Bengio et al. | Hinton, G., Vinyals, O. & Dean, J. |
| 类型≠ | Training strategy | Neural network compression (teacher–student) |
| 开创性文献≠ | Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009). Curriculum learning. International Conference on Machine Learning (ICML), 41–48. DOI ↗ | Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗ |
| 别名 | Scheduled Training, Difficulty-Based Training, Self-Paced Learning, Müfredat Öğrenimi | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation |
| 相关≠ | 3 | 5 |
| 摘要≠ | Curriculum Learning is a training strategy for machine learning models, introduced by Bengio et al. in 2009, in which training examples are presented in a meaningful order—typically from easy to hard—rather than at random. Inspired by how humans and animals learn progressively, it organizes training data into a curriculum that starts with simpler, cleaner, or more representative samples and gradually introduces harder or more complex examples as the model matures. | Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster. |
| ScholarGate数据集 ↗ |
|
|