In this paper, we present COSMOS, a novel architecture for macroprogramming heterogeneous sensor network systems. Macroprogramming entails aggregate system behavior specification...
Next generation communication systems must support diverse applications operating over high-performance local, metropolitan, and wide area networks. This paper describes a framewo...
Douglas C. Schmidt, Burkhard Stiller, Tatsuya Suda...
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...
Abstract-- A major drawback of artificial neural networks (ANNs) is their black-box character. This is especially true for recurrent neural networks (RNNs) because of their intrica...
The emergence of networked devices in the home has made it possible to develop applications that control a variety of household functions. However, current devices communicate via ...