no code implementations • 19 Dec 2023 • Zezhong Zhang, Feng Bao, Guannan Zhang
The impressive expressive power of deep neural networks (DNNs) underlies their widespread applicability.
no code implementations • 22 Oct 2023 • Yanfang Liu, Minglei Yang, Zezhong Zhang, Feng Bao, Yanzhao Cao, Guannan Zhang
Unlike existing diffusion models that train neural networks to learn the score function, we develop a training-free score estimation method.
1 code implementation • 2 Sep 2023 • Feng Bao, Zezhong Zhang, Guannan Zhang
A major drawback of existing filtering methods, e. g., particle filters or ensemble Kalman filters, is the low accuracy in handling high-dimensional and highly nonlinear problems.
no code implementations • 27 Jan 2023 • Zezhong Zhang, Feng Bao, Lili Ju, Guannan Zhang
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.
1 code implementation • 17 Dec 2022 • Richard Archibald, Feng Bao, Yanzhao Cao, Hui Sun
In this paper, we carry out numerical analysis to prove convergence of a novel sample-wise back-propagation method for training a class of stochastic neural networks (SNNs).
no code implementations • 25 Jan 2022 • Richard Archibald, Feng Bao
In this paper, we develop a kernel learning backward SDE filter method to estimate the state of a stochastic dynamical system based on its partial noisy observations.
1 code implementation • 17 May 2021 • Feng Bao
Multiview data contain information from multiple modalities and have potentials to provide more comprehensive features for diverse machine learning tasks.
no code implementations • 28 Nov 2020 • Richard Archibald, Feng Bao, Yanzhao Cao, He Zhang
We develop a probabilistic machine learning method, which formulates a class of stochastic neural networks by a stochastic optimal control problem.
1 code implementation • 3 Nov 2020 • Hu Hu, Chao-Han Huck Yang, Xianjun Xia, Xue Bai, Xin Tang, Yajian Wang, Shutong Niu, Li Chai, Juanjuan Li, Hongning Zhu, Feng Bao, Yuanjun Zhao, Sabato Marco Siniscalchi, Yannan Wang, Jun Du, Chin-Hui Lee
To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed.
Ranked #1 on Acoustic Scene Classification on TAU Urban Acoustic Scenes 2019 (using extra training data)
1 code implementation • 16 Jul 2020 • Hu Hu, Chao-Han Huck Yang, Xianjun Xia, Xue Bai, Xin Tang, Yajian Wang, Shutong Niu, Li Chai, Juanjuan Li, Hongning Zhu, Feng Bao, Yuanjun Zhao, Sabato Marco Siniscalchi, Yannan Wang, Jun Du, Chin-Hui Lee
On Task 1b development data set, we achieve an accuracy of 96. 7\% with a model size smaller than 500KB.