방법 비교

	다중 작업 학습 (Multitask Learning, MTL)	커리큘럼 학습	지식 증류
분야	딥러닝	딥러닝	딥러닝
계열	Machine learning	Machine learning	Machine learning
기원 연도	1997	2009	2015
창시자	Rich Caruana	Yoshua Bengio et al.	Hinton, G., Vinyals, O. & Dean, J.
유형	Inductive transfer method	Training strategy	Neural network compression (teacher–student)
원전	Caruana, R. (1997). Multitask learning. Machine Learning, 28(1), 41–75.	Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009). Curriculum learning. International Conference on Machine Learning (ICML), 41–48.	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.
별칭	MTL, Joint Learning, Shared Representation Learning, Çok Görevli Öğrenme	Scheduled Training, Difficulty-Based Training, Self-Paced Learning, Müfredat Öğrenimi	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
관련	3	3	5
요약	Multitask Learning (MTL) is a machine learning paradigm in which a model is trained simultaneously on multiple related tasks, sharing representations across them to improve generalization. Introduced formally by Rich Caruana in 1997, MTL draws on the intuition that auxiliary tasks act as inductive bias, providing extra supervision signals that help the shared layers learn richer, more robust feature representations than single-task training would yield.	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.