ScholarGate
Asystent

Porównaj metody

Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.

Uczenie się według programu nauczania×Uczenie wielozadaniowe×
DziedzinaUczenie głębokieUczenie głębokie
RodzinaMachine learningMachine learning
Rok powstania20091997
TwórcaYoshua Bengio et al.Rich Caruana
TypTraining strategyInductive transfer method
Źródło pierwotneBengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009). Curriculum learning. International Conference on Machine Learning (ICML), 41–48. DOI ↗Caruana, R. (1997). Multitask learning. Machine Learning, 28(1), 41–75. DOI ↗
Inne nazwyScheduled Training, Difficulty-Based Training, Self-Paced Learning, Müfredat ÖğrenimiMTL, Joint Learning, Shared Representation Learning, Çok Görevli Öğrenme
Pokrewne33
PodsumowanieCurriculum 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.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.
ScholarGateZbiór danych
  1. v1
  2. 1 Źródła
  3. PUBLISHED
  1. v1
  2. 1 Źródła
  3. PUBLISHED

Przejdź do wyszukiwania Pobierz slajdy

ScholarGatePorównaj metody: Curriculum Learning · Multitask Learning. Pobrano 2026-06-15 z https://scholargate.app/pl/compare