Inspired by the relation between deep neural network (DNN) and partial
d...
Most existing semi-supervised graph-based clustering methods exploit the...
Training deep neural networks (DNNs) is an important and challenging
opt...
The dynamic formulation of optimal transport has attracted growing inter...
Collecting paired training data is difficult in practice, but the unpair...
The Chan-Vese (CV) model is a classic region-based method in image
segme...
Continual learning aims to learn a sequence of tasks from dynamic data
d...
Interpreting deep neural networks from the ordinary differential equatio...
The multiple-input multiple-output (MIMO) detection problem, a fundament...
Although ordinary differential equations (ODEs) provide insights for
des...
Finding the stationary states of a free energy functional is an essentia...
Finding the stationary states of a free energy functional is an importan...
Existing domain adaptation methods aim at learning features that can be
...
Many existing interpretation methods of convolutional neural networks (C...
Computing stationary states is an important topic for phase field crysta...
A human does not have to see all elephants to recognize an animal as an
...
Convolutional neural networks have been widely deployed in various
appli...
As a fundamental problem of natural language processing, it is important...
Quantitative susceptibility mapping (QSM) uses the phase data in magneti...