开课单位--华盛顿州立大学
1 1/1

1
Voxel Deconvolutional Networks for 3D Brain Image Labeling[用于3D脑图像标记的体素反卷积网络]
  Yongjun Chen(华盛顿州立大学) Deep learning methods have shown great success in pixel-wise prediction tasks. One of the most popular methods employs an encoder-decoder network in w...
热度:35

2
Smoothed Dilated Convolutions for Improved Dense Prediction[用于改进密集预测的平滑扩张卷积]
  Zhengyang Wang(华盛顿州立大学) Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various tasks lik...
热度:45

3
Adaptive Dimension Reduction Using Discriminant Analysis and K-means Clustering[基于判别分析和K均值聚类的自适应降维方法]
  Shuiwang Ji(华盛顿州立大学) Regularized Kernel Discriminant Analysis (RKDA) performs linear discriminant analysis in the feature space via the kernel trick. The performance of RK...
热度:47

4
An Accelerated Gradient Method for Trace Norm Minimization[一种用于迹线范数最小化的加速梯度法]
  Shuiwang Ji(华盛顿州立大学) We consider the minimization of a smooth loss function regularized by the trace norm of the matrix variable. Such formulation finds applications in ma...
热度:158

5
A Least Squares Formulation for Canonical Correlation Analysis[典型相关分析的最小二乘公式]
  Shuiwang Ji(华盛顿州立大学) Canonical Correlation Analysis (CCA) is a well-known technique for finding the correlations between two sets of multi-dimensional variables. It projec...
热度:90
1 1/1