نمونه متن انگلیسی مقاله
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 both an effect on the speed of convergence of the training process to a minimum and, in the case of non-convex criteria, on the quality of the local minima obtained: curriculum learning can be seen as a particular form of continuation method (a general strategy for global optimization of nonconvex functions).
Humans need about two decades to be trained as fully functional adults of our society. That training is highly organized, based on an education system and a curriculum which introduces different concepts at different times, exploiting previously learned concepts to ease the learning of new abstractions. By choosing which examples to present and in which order to present them to the learning system, one can guide training and remarkably increase the speed at which learning can occur. This idea is routinely exploited in animal training where it is called shaping (Skinner, 1958; Peterson, 2004).