* This paper has been withdrawn by the author due to a lack of full empirical evaluation. More advanced method has been developed. This method has been fully out of date

**Click to Read Paper and Get Code**

Transfer Learning for Voice Activity Detection: A Denoising Deep Neural Network Perspective

Mar 08, 2013

Xiao-Lei Zhang, Ji Wu

Mar 08, 2013

Xiao-Lei Zhang, Ji Wu

* This paper has been submitted to the conference "INTERSPEECH2013" in March 4, 2013 for review

**Click to Read Paper and Get Code**

* This paper has been accepted by IEEE ICASSP-2013, and will be published online after May, 2013

**Click to Read Paper and Get Code**

Barron Spaces and the Compositional Function Spaces for Neural Network Models

Jun 18, 2019

Weinan E, Chao Ma, Lei Wu

One of the key issues in the analysis of machine learning models is to identify the appropriate function space for the model. This is the space of functions that the particular machine learning model can approximate with good accuracy, endowed with a natural norm associated with the approximation process. In this paper, we address this issue for two representative neural network models: the two-layer networks and the residual neural networks. We define Barron space and show that it is the right space for two-layer neural network models in the sense that optimal direct and inverse approximation theorems hold for functions in the Barron space. For residual neural network models, we construct the so-called compositional function space, and prove direct and inverse approximation theorems for this space. In addition, we show that the Rademacher complexity has the optimal upper bounds for these spaces.
Jun 18, 2019

Weinan E, Chao Ma, Lei Wu

**Click to Read Paper and Get Code**

3D Dense Separated Convolution Module for Volumetric Image Analysis

May 14, 2019

Lei Qu, Changfeng Wu, Liang Zou

May 14, 2019

Lei Qu, Changfeng Wu, Liang Zou

* 7 pages,5 figures

**Click to Read Paper and Get Code**

A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics

Apr 08, 2019

Weinan E, Chao Ma, Lei Wu

Apr 08, 2019

Weinan E, Chao Ma, Lei Wu

* 30 pages, 5 figures

**Click to Read Paper and Get Code**

* 8 pages

**Click to Read Paper and Get Code**

A Priori Estimates of the Generalization Error for Two-layer Neural Networks

Oct 15, 2018

Weinan E, Chao Ma, Lei Wu

New estimates for the generalization error are established for the two-layer neural network model. These new estimates are a priori in nature in the sense that the bounds depend only on some norms of the underlying functions to be fitted, not the parameters in the model. In contrast, most existing results for neural networks are a posteriori in nature in the sense that the bounds depend on some norms of the model parameters. The error rates are comparable to that of the Monte Carlo method for integration problems. Moreover, these bounds are equally effective in the over-parametrized regime when the network size is much larger than the size of the dataset.
Oct 15, 2018

Weinan E, Chao Ma, Lei Wu

* 14 pages, 2 figures

**Click to Read Paper and Get Code**

Solving Statistical Mechanics using Variational Autoregressive Networks

Sep 27, 2018

Dian Wu, Lei Wang, Pan Zhang

Sep 27, 2018

Dian Wu, Lei Wang, Pan Zhang

**Click to Read Paper and Get Code**

Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes

Nov 28, 2017

Lei Wu, Zhanxing Zhu, Weinan E

Nov 28, 2017

Lei Wu, Zhanxing Zhu, Weinan E

**Click to Read Paper and Get Code**

Learning Theory of Distributed Regression with Bias Corrected Regularization Kernel Network

Aug 07, 2017

Zhengchu Guo, Lei Shi, Qiang Wu

Aug 07, 2017

Zhengchu Guo, Lei Shi, Qiang Wu

**Click to Read Paper and Get Code**

Dual Attention MobDenseNet(DAMDNet) for Robust 3D Face Alignment

Aug 30, 2019

Lei Jiang Xiao-Jun Wu Josef Kittler

Aug 30, 2019

Lei Jiang Xiao-Jun Wu Josef Kittler

* ICCV2019 workshop

* 10 pages

**Click to Read Paper and Get Code**

Turbo Learning for Captionbot and Drawingbot

May 21, 2018

Qiuyuan Huang, Pengchuan Zhang, Dapeng Wu, Lei Zhang

May 21, 2018

Qiuyuan Huang, Pengchuan Zhang, Dapeng Wu, Lei Zhang

**Click to Read Paper and Get Code**

* 11 pages, 3 figures. Accepted to NAACL 2018

**Click to Read Paper and Get Code**

DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model

Dec 10, 2017

Bo Wu, Yang Liu, Bo Lang, Lei Huang

Dec 10, 2017

Bo Wu, Yang Liu, Bo Lang, Lei Huang

* 16 pages,8 figures

**Click to Read Paper and Get Code**

Plug and Play! A Simple, Universal Model for Energy Disaggregation

Apr 07, 2014

Guoming Tang, Kui Wu, Jingsheng Lei, Jiuyang Tang

Apr 07, 2014

Guoming Tang, Kui Wu, Jingsheng Lei, Jiuyang Tang

* 12 pages, 5 figures, and 4 tables

**Click to Read Paper and Get Code**

Analysis of the Gradient Descent Algorithm for a Deep Neural Network Model with Skip-connections

Apr 14, 2019

Weinan E, Chao Ma, Qingcan Wang, Lei Wu

Apr 14, 2019

Weinan E, Chao Ma, Qingcan Wang, Lei Wu

* 29 pages, 4 figures

**Click to Read Paper and Get Code**

Quality-aware Unpaired Image-to-Image Translation

Mar 15, 2019

Lei Chen, Le Wu, Zhenzhen Hu, Meng Wang

Mar 15, 2019

Lei Chen, Le Wu, Zhenzhen Hu, Meng Wang

* IEEE Transactions on Multimedia

**Click to Read Paper and Get Code**

AAANE: Attention-based Adversarial Autoencoder for Multi-scale Network Embedding

Mar 24, 2018

Lei Sang, Min Xu, Shengsheng Qian, Xindong Wu

Mar 24, 2018

Lei Sang, Min Xu, Shengsheng Qian, Xindong Wu

* 8 pages, 5 figures

**Click to Read Paper and Get Code**

Understanding and Enhancing the Transferability of Adversarial Examples

Feb 27, 2018

Lei Wu, Zhanxing Zhu, Cheng Tai, Weinan E

Feb 27, 2018

Lei Wu, Zhanxing Zhu, Cheng Tai, Weinan E

* 15 pages

**Click to Read Paper and Get Code**