Information-theoretic regularization for learning global features by sequential VAE
Sign Up to like & getrecommendations! Published in 2021 at "Machine Learning"
DOI: 10.1007/s10994-021-06032-4
Abstract: Sequential variational autoencoders (VAEs) with a global latent variable z have been studied for disentangling the global features of data, which is useful for several downstream tasks. To further assist the sequential VAEs in obtaining… read more here.
Keywords: information; sequential vaes; global features; information theoretic ... See more keywords