Auxiliary deep generative models
Deep generative models parameterized by neural networks have achieved state-of-the-art performance in unsupervised and semi-supervised learning.
Authors: Lars Maaløe, Marco Fraccaro, Ole Winther
Deep generative models parameterized by neural networks have achieved state-of-the-art performance in unsupervised and semi-supervised learning.
Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs.
Humans possess an ability to abstractly reason about objects and their interactions, an ability not shared with state-of-the-art deep learning models