论文标题
在耦合的变异自动编码器中使用学生的T-分布在潜在层
Use of Student's t-Distribution for the Latent Layer in a Coupled Variational Autoencoder
论文作者
论文摘要
结合了广义损耗函数和潜在层分布的耦合变异自动编码器，显示出生成的MNIST数字复制品的准确性和鲁棒性的提高。潜在层使用学生的T-分布来结合重尾腐烂。损耗函数使用耦合对数，从而增加对异常可能性的图像的惩罚。生成图像的可能性的普遍平均值用于衡量算法的决定性，准确性和鲁棒性的性能。
A Coupled Variational Autoencoder, which incorporates both a generalized loss function and latent layer distribution, shows improvement in the accuracy and robustness of generated replicas of MNIST numerals. The latent layer uses a Student's t-distribution to incorporate heavy-tail decay. The loss function uses a coupled logarithm, which increases the penalty on images with outlier likelihood. The generalized mean of the generated image's likelihood is used to measure the performance of the algorithm's decisiveness, accuracy, and robustness.
