Semi-supervised classification uses aspects of both unsupervised and supervised learning to improve upon the performance of traditional classification methods. Semi-supervised clu...
— Multiple description coding (MDC) has emerged as a powerful technique for reliable real-time communications over lossy packet networks. In its basic form, it involves encoding ...
We investigate classification of non-linguistic vocalisations with a novel audiovisual approach and Long Short-Term Memory (LSTM) Recurrent Neural Networks as highly successful d...
We introduce quadratically gated mixture of experts (QGME), a statistical model for multi-class nonlinear classification. The QGME is formulated in the setting of incomplete data,...
Multi-path routing allows building and use of multiple paths for routing between a source-destination pair. This paper investigates the problem of selecting multiple routing paths ...