RNADE：实值神经自回归密度估计器
RNADE: The real-valued neural autoregressive density-estimator
摘要：
介绍了一种新的实值向量联合密度估计模型--RNADE。我们的模型将数据点的密度计算为使用具有共享参数的混合密度网络建模的一维条件的乘积。RNADE学习数据的分布式表示，同时具有用于计算密度的易于处理的表达式。易于处理的可能性允许与其他方法进行直接比较，并通过标准的基于梯度的优化器进行训练。我们比较了RNADE在几个异构和感知数据集上的性能，发现它在所有情况下都优于混合模型，只有一种情况除外。
英文摘要：
We introduce RNADE, a new model for joint density estimation of real-valued vectors. Our model calculates the density of a datapoint as the product of one-dimensional conditionals modeled using mixture density networks with shared parameters. RNADE learns a distributed representation of the data, while having a tractable expression for the calculation of densities. A tractable likelihood allows direct comparison with other methods and training by standard gradient-based optimizers. We compare the performance of RNADE on several datasets of heterogeneous and perceptual data, finding it outperforms mixture models in all but one case.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
