论文标题
技术报告：具有完整协方差矩阵的培训混合物密度网络
Technical report: Training Mixture Density Networks with full covariance matrices
论文作者
论文摘要
混合物密度网络是一种试用和测试的工具，用于建模有条件的概率分布。因此，它们构成了解决这个问题的新方法的绝佳基准。在标准配方中，MDN采用一些输入和输出参数，用于对混合物组件的协方差限制的高斯混合模型。由于随机变量之间的协方差是我们正在研究的条件建模问题中的一个核心问题，因此我得出并实施了具有不受限制协方差的MDN公式。这很可能以前已经做过，但是我在网上找不到任何资源。因此，我以本技术报告的形式记录了我的方法，希望它对面临类似情况的其他人可能有用。
Mixture Density Networks are a tried and tested tool for modelling conditional probability distributions. As such, they constitute a great baseline for novel approaches to this problem. In the standard formulation, an MDN takes some input and outputs parameters for a Gaussian mixture model with restrictions on the mixture components' covariance. Since covariance between random variables is a central issue in the conditional modeling problems we were investigating, I derived and implemented an MDN formulation with unrestricted covariances. It is likely that this has been done before, but I could not find any resources online. For this reason, I have documented my approach in the form of this technical report, in hopes that it may be useful to others facing a similar situation.
