This paper introduces an approach called Clustering and Co-evolution to Construct Neural Network Ensembles (CONE). This approach creates neural network ensembles in an innovative ...
The probability that a term appears in relevant documents ( ) is a fundamental quantity in several probabilistic retrieval models, however it is difficult to estimate without rele...
In this paper we address the problem of estimating who is speaking from automatically extracted low resolution visual cues in group meetings. Traditionally, the task of speech/non...
— Sampling-based kinodynamic planners, such as the popular RRT algorithm, have been proposed as promising solutions to planning for systems with dynamics. Nevertheless, complex s...
— Interaction of a robot with dynamic environments would require continuous adaptation of force and impedance, which is generally not available in current robot systems. In contr...