— We investigate modeling and recognition of object manipulation actions for the purpose of imitation based learning in robotics. To model the process, we are using a combination...
We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear. W...
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
This paper describes a system which converts a twodimensional sketch with hidden lines removed of a single polyhedral object into a boundary representation solid model. The system...
We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...