标题： 技术报告：使用完整协方差矩阵训练混合密度网络 显示英文标题

标题： Technical report: Training Mixture Density Networks with full covariance matrices

摘要： 混合密度网络是一种经过验证的用于建模条件概率分布的工具。 因此，它们是该问题新方法的一个很好的基线。 在标准形式中，一个MDN接收一些输入并输出具有对混合分量协方差限制的高斯混合模型的参数。 由于随机变量之间的协方差是我们所研究的条件建模问题中的核心问题，我推导并实现了一个具有无约束协方差的MDN形式。 很可能这已经被以前的人做过，但我没有找到任何在线资源。 因此，我以技术报告的形式记录了我的方法，希望它可能对面临类似情况的其他人有所帮助。 显示英文摘要

摘要： 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.