arXiv:1603.06653cs.LG
Information Theoretic-Learning Auto-Encoder
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
We propose Information Theoretic-Learning (ITL) divergence measures for variational regularization of neural networks. We also explore ITL-regularized autoencoders as an alternative to variational autoencoding bayes, adversarial autoencoders and generative adversarial networks for randomly generating sample data without explicitly defining a partition function. This paper also formalizes, generative moment matching networks under the ITL framework.
Not affiliated, but I found the paper. First link to gitxiv is the abstract of a paper on arxiv. Here is the paper with more detail: http://arxiv.org/abs/1603.06653
daveguyView on HNParent context