2 citations · 9 across the 17 of their papers we have counts for
5 papers · 1 filter
Improving the Expressive Power of Deep Neural Networks through Integral Activation Transform
Zezhong Zhang, Feng Bao, Guannan Zhang
The impressive expressive power of deep neural networks (DNNs) underlies their widespread applicability. However, while the theoretical capacity of deep architectures is high, the…
A Unified Filter Method for Jointly Estimating State and Parameters of Stochastic Dynamical Systems via the Ensemble Score Filter
Feng Bao, Guannan Zhang, Zezhong Zhang
This paper tackles the intricate task of jointly estimating state and parameters in data assimilation for stochastic dynamical systems that are affected by noise and observed only…
Diffusion-Model-Assisted Supervised Learning of Generative Models for Density Estimation
Yanfang Liu, Minglei Yang, Zezhong Zhang +3
We present a supervised learning framework of training generative models for density estimation. Generative models, including generative adversarial networks, normalizing flows, va…
An Ensemble Score Filter for Tracking High-Dimensional Nonlinear Dynamical Systems
Feng Bao, Zezhong Zhang, Guannan Zhang
We propose an ensemble score filter (EnSF) for solving high-dimensional nonlinear filtering problems with superior accuracy. A major drawback of existing filtering methods, e.g., p…
TransNet: Transferable Neural Networks for Partial Differential Equations
Zezhong Zhang, Feng Bao, Lili Ju +1
Transfer learning for partial differential equations (PDEs) is to develop a pre-trained neural network that can be used to solve a wide class of PDEs. Existing transfer learning ap…