ScholarGate
Ассистент

Сравнение методов

Просматривайте выбранные методы рядом; строки с различиями подсвечены.

Обучение по учебному плану×Мультизадачное обучение×
ОбластьГлубокое обучениеГлубокое обучение
СемействоMachine learningMachine learning
Год появления20091997
Автор методаYoshua Bengio et al.Rich Caruana
ТипTraining strategyInductive transfer method
Основополагающий источникBengio, 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 ↗
Другие названияScheduled Training, Difficulty-Based Training, Self-Paced Learning, Müfredat ÖğrenimiMTL, Joint Learning, Shared Representation Learning, Çok Görevli Öğrenme
Связанные33
СводкаCurriculum 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.
ScholarGateНабор данных
  1. v1
  2. 1 Источники
  3. PUBLISHED
  1. v1
  2. 1 Источники
  3. PUBLISHED

Перейти к поиску Скачать слайды

ScholarGateСравнение методов: Curriculum Learning · Multitask Learning. Получено 2026-06-15 из https://scholargate.app/ru/compare