资源分类
》 资源 》论文》RNADE: The real-valued neural autoregressive density-estimator

RNADE: The real-valued neural autoregressive density-estimator

2020-01-16 | |  68 |   43 |   0

Abstract

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 onedimensional 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 gradientbased 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.

上一篇：Fisher-Optimal Neural Population Codes for High-Dimensional Diffeomorphic Stimulus Representations

下一篇：Online Robust PCA via Stochastic Optimization

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...