Learning theory and programs to date are inductively bounded: they can be described as "wind-up toys" which can only learn the kinds of things that their designers envisi...
This paper presents an integrated modeling framework where the learning and knowledge retrieval mechanisms of the ACT-R cognitive architecture are combined with a semantic resource...
State-of-the-art pattern recognition methods have difficulty dealing with problems where the dimension of the output space is large. In this article, we propose a new framework ba...
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
Abstract. Learning Design offers the possibility of capturing the process, activities, user organization and resources used in a learning experience. But a wider set of scenarios a...