Estimating divergence between two point processes, i.e. probability laws on the space of spike trains, is an essential tool in many computational neuroscience applications, such a...
In this paper, we present a new co-training strategy that makes use of unlabelled data. It trains two predictors in parallel, with each predictor labelling the unlabelled data for...
Abstract— This paper describes a novel approach for incremental learning of human motion pattern primitives through on-line observation of human motion. The observed motion time ...
The motivation and objective for this paper is to demonstrate “Personal High Performance Computing (PHPC)”, which requires only a smaller number of computers, resources and sp...
Consider a heterogeneous cluster system, consisting of processors with varying processing capabilities and network links with varying bandwidths. Given a DAG application to be sch...