arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.07448cs.LG
收藏

最大熵自动编码

Maximum Entropy Auto-Encoding

Fraunhofer FKIE(弗劳恩霍夫通信、信息处理和人机工程学研究所)

Paul M Baggenstoss

摘要:

在本文中,它表明,使用最佳重建的自动编码器显着优于传统的自动编码器。最佳重建使用给定特征的输入的条件平均值,在最大熵先验分布下。最优重构网络称为确定性投影置信网络(D-PBN),它类似于标准重构网络,但具有特殊的非线性,需要迭代求解。该方法可以看作是最大熵图像重建的推广,并可扩展到多层。在实验中,均方重建误差减少了高达两倍。对于更深的网络,或者对于具有无约束值的输入数据(高斯假设),性能改进会减少。

英文摘要:

In this paper, it is shown that an auto-encoder using optimal reconstruction significantly outperforms a conventional auto-encoder. Optimal reconstruction uses the conditional mean of the input given the features, under a maximum entropy prior distribution. The optimal reconstruction network, which is called deterministic projected belied network (D-PBN), resembles a standard reconstruction network, but with special non-linearities that mist be iteratively solved. The method, which can be seen as a generalization of maximum entropy image reconstruction, extends to multiple layers. In experiments, mean square reconstruction error reduced by up to a factor of two. The performance improvement diminishes for deeper networks, or for input data with unconstrained values (Gaussian assumption).

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。

↑