Semantic Scholar uses AI to extract papers important to this topic.
Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video… Expand The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative… Expand We propose an anomaly detection method using the reconstruction probability from the variational autoencoder. The reconstruction… Expand In this paper, we propose the “adversarial autoencoder” (AAE), which is a probabilistic autoencoder that uses the recently… Expand Natural language generation of coherent long texts like paragraphs or longer documents is a challenging problem for recurrent… Expand We previously have applied deep autoencoder (DAE) for noise reduction and speech enhancement. However, the DAE was trained using… Expand Autoencoders play a fundamental role in unsupervised learning and in deep architectures for transfer learning and other tasks. In… Expand We explore an original strategy for building deep networks, based on stacking layers of denoising autoencoders which are trained… Expand Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial… Expand An autoencoder network uses a set of recognition weights to convert an input vector into a code vector. It then uses a set of… Expand