Abstract

We develop/propose the method reducing the dimension of a data matrix, based on its direct and inverse projection, and the calculation of projectors that minimize the cross-entropy functional, remove. We introduce the concept of information capacity of a matrix, which is used as a constraint in the optimal reduction problem, is introduced. The proposed method is compared with known methods in the problem of binary classification.

中文翻译：

---

限制投影仪信息容量及其范数的数据矩阵的交叉熵约简

摘要

我们开发/提出了减少数据矩阵维数的方法，基于其直接和逆投影，以及最小化交叉熵函数的投影仪的计算，删除。我们引入了矩阵的信息容量的概念，它被用作优化约简问题中的约束。在二元分类问题中将所提出的方法与已知方法进行比较。