This paper proposes a new concept in hierarchical representations that exploits features of different granularity and specificity coming from all layers of the hierarchy. The conc...
We present a generalization of the nonnegative matrix factorization (NMF), where a multilayer generative network with nonnegative weights is used to approximate the observed nonne...
In this paper we present the results of a comparative study that explores the potential benefits of using embodied ion to help children, aged 7 to 10, learn abstract concepts rela...
Abstract. Modeling the statistical structure of natural images is interesting for reasons related to neuroscience as well as engineering. Currently, this modeling relies heavily on...
We present the design of a new web application framework for collaborative learning. The framework guides users (i.e. teachers) in implementing online activities based on well-know...