Z Long, Y Lu, X Ma, B Dong - International conference on …, 2018 - proceedings.mlr.press
Partial differential equations (PDEs) play a prominent role in many disciplines of science and engineering. PDEs are commonly derived based on empirical observations. However …
The process of transforming observed data into predictive mathematical models of the physical world has always been paramount in science and engineering. Although data is …
Recently, deep residual networks have been successfully applied in many computer vision and natural language processing tasks, pushing the state-of-the-art performance with …
E Weinan, J Han, Q Li - arXiv preprint arXiv:1807.01083, 2018 - researchgate.net
Recent work linking deep neural networks and dynamical systems opened up new avenues to analyze deep learning. In particular, it is observed that new insights can be obtained by …
Neural networks have been very successful in many applications; we often, however, lack a theoretical understanding of what the neural networks are actually learning. This problem …
In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels in one model. The proposed control …
L Zhang, L Wang - arXiv preprint arXiv:1809.10188, 2018 - arxiv.org
We present a deep generative model, named Monge-Amp\ere flow, which builds on continuous-time gradient flow arising from the Monge-Amp\ere equation in optimal transport …
A Nitanda, T Suzuki - International Conference on Machine …, 2018 - proceedings.mlr.press
Abstract Residual Networks (ResNets) have become state-of-the-art models in deep learning and several theoretical studies have been devoted to understanding why ResNet …
Q Sun, Y Tao, Q Du - arXiv preprint arXiv:1812.00174, 2018 - arxiv.org
During the last few years, significant attention has been paid to the stochastic training of artificial neural networks, which is known as an effective regularization approach that helps …