Variational autoencoders trained to minimize the reconstruction error are sensitive to the posterior collapse problem, that is the proposal posterior distribution is always equal to the prior. We propose a novel regularization method based on fraternal dropout to prevent posterior collapse. We evaluate our approach using several metrics and observe improvements in all the tested configurations.

翻译：为尽量减少重建错误而培训的变式自动编码器对后方崩溃问题十分敏感,即后方分配建议总是与前方相同。我们提出了基于兄弟辍学的新颖的正规化方法,以防止后方崩溃。我们用若干度量来评估我们的方法,并观察所有经过测试的配置的改进。