互信息(Mutual Information)是信息论里一种有用的信息度量,它可以看成是一个随机变量中包含的关于另一个随机变量的信息量,或者说是一个随机变量由于已知另一个随机变量而减少的不肯定性.

VIP内容

简介:互信息(Mutual Information)是信息论里一种有用的信息度量,它可以看成是一个随机变量中包含的关于另一个随机变量的信息量,或者说是一个随机变量由于已知另一个随机变量而减少的不肯定性.本教程中运用深度最大化信息的方法来对输入的图片和它的表示有一个很好的表征学习。针对互信息的精准计算、最大化整个图像输入和输出表示之间的互信息等问题都提出了合理的解决方案。

成为VIP会员查看完整内容
0
18

最新内容

Feature ranking and selection is a widely used approach in various applications of supervised dimensionality reduction in discriminative machine learning. Nevertheless there exists significant evidence on feature ranking and selection algorithms based on any criterion leading to potentially sub-optimal solutions for class separability. In that regard, we introduce emerging information theoretic feature transformation protocols as an end-to-end neural network training approach. We present a dimensionality reduction network (MMINet) training procedure based on the stochastic estimate of the mutual information gradient. The network projects high-dimensional features onto an output feature space where lower dimensional representations of features carry maximum mutual information with their associated class labels. Furthermore, we formulate the training objective to be estimated non-parametrically with no distributional assumptions. We experimentally evaluate our method with applications to high-dimensional biological data sets, and relate it to conventional feature selection algorithms to form a special case of our approach.

0
0
下载
预览

最新论文

Feature ranking and selection is a widely used approach in various applications of supervised dimensionality reduction in discriminative machine learning. Nevertheless there exists significant evidence on feature ranking and selection algorithms based on any criterion leading to potentially sub-optimal solutions for class separability. In that regard, we introduce emerging information theoretic feature transformation protocols as an end-to-end neural network training approach. We present a dimensionality reduction network (MMINet) training procedure based on the stochastic estimate of the mutual information gradient. The network projects high-dimensional features onto an output feature space where lower dimensional representations of features carry maximum mutual information with their associated class labels. Furthermore, we formulate the training objective to be estimated non-parametrically with no distributional assumptions. We experimentally evaluate our method with applications to high-dimensional biological data sets, and relate it to conventional feature selection algorithms to form a special case of our approach.

0
0
下载
预览
Top