We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...
Abstract—Many important real-world systems, modeled naturally as complex networks, have heterogeneous interactions and complicated dependency structures. Link prediction in such ...
Darcy A. Davis, Ryan Lichtenwalter, Nitesh V. Chaw...
Integrated architectures in the automotive and avionic domain promise improved resource utilization and enable a better coordination of application subsystems compared to federated...
Multimodal interfaces are designed with a focus on flexibility, although very few currently are capable of adapting to major sources of user, task, or environmental variation. The...
Abstract Weproposeacomputationalmodelofcontourintegration for visual saliency. The model uses biologically plausible devices to simulate how the representations of elements aligned...