Activity recognition is a key component for creating intelligent, multi-agent systems. Intrinsically, activity recognition is a temporal classification problem. In this paper, we...
Douglas L. Vail, Manuela M. Veloso, John D. Laffer...
The learning of probabilistic models with many hidden variables and nondecomposable dependencies is an important and challenging problem. In contrast to traditional approaches bas...
Bayesian learning in undirected graphical models--computing posterior distributions over parameters and predictive quantities-is exceptionally difficult. We conjecture that for ge...
Abstract. We develop a probabilistic interpretation of non-linear component extraction in neural networks that activate their hidden units according to a softmaxlike mechanism. On ...
Recognition of chatting activities in social interactions is useful for constructing human social networks. However, the existence of multiple people involved in multiple dialogue...