During the recent decade, deep learning technology, particularly deep neural network (DNN), has gained tremendous popularity in various fields including signal processing (SP). As a data-driven ...

Dealing with uncertainty is crucial for survival where significant individual differences exist. In general, people show a preference for options with higher variance (uncertainty), known as a ...

remove-circle Internet Archive's in-browser video "theater" requires JavaScript to be enabled. It appears your browser does not have it turned on. Please see your ...

We introduce a supervised learning framework for target functions that are well approximated by a sum of (few) separable terms. The framework proposes to approximate each component function by a ...

Functional near-infrared spectroscopy (fNIRS) has attracted increasing attention in the field of brain–computer interfaces (BCIs) owing to their advantages such as non-invasiveness, user safety, ...

We introduce a large-margin softmax (L-Softmax) loss for convolutional neural networks. L-Softmax loss can greatly improve the generalization ability of CNNs, so it is very suitable for general ...