publication . Conference object . Other literature type . 2009

curriculum learning

Bengio, Yoshua; Louradour, Jérôme; Collobert, Ronan; Weston, Jason;
  • Published: 01 Jan 2009
  • Publisher: ACM Press
Humans and animals learn much better when the examples are not randomly presented but organized in a meaningful order which illustrates gradually more concepts, and gradually more complex ones. Here, we formalize such training strategies in the context of machine learning, and call them "curriculum learning". In the context of recent research studying the difficulty of training in the presence of non-convex training criteria (for deep deterministic and stochastic neural networks), we explore curriculum learning in various set-ups. The experiments show that significant improvements in generalization can be achieved. We hypothesize that curriculum learning has bot...
free text keywords: Curriculum, Stability (learning theory), Active learning, Stochastic neural network, Instance-based learning, Global optimization, Maxima and minima, Machine learning, computer.software_genre, computer, Artificial intelligence, business.industry, business, Convergence (routing), Computer science
Related Organizations
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue