ScholarGate
Assistent

Methoden vergelijken

Bekijk de geselecteerde methoden naast elkaar; rijen die verschillen zijn gemarkeerd.

Curriculum Learning×Multitask Leren×
VakgebiedDeep learningDeep learning
FamilieMachine learningMachine learning
Jaar van ontstaan20091997
GrondleggerYoshua Bengio et al.Rich Caruana
TypeTraining strategyInductive transfer method
Oorspronkelijke bronBengio, 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 ↗
AliassenScheduled Training, Difficulty-Based Training, Self-Paced Learning, Müfredat ÖğrenimiMTL, Joint Learning, Shared Representation Learning, Çok Görevli Öğrenme
Verwant33
SamenvattingCurriculum 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.
ScholarGateGegevensset
  1. v1
  2. 1 Bronnen
  3. PUBLISHED
  1. v1
  2. 1 Bronnen
  3. PUBLISHED

Naar zoeken Dia's downloaden

ScholarGateMethoden vergelijken: Curriculum Learning · Multitask Learning. Geraadpleegd op 2026-06-15 via https://scholargate.app/nl/compare