← Search

Tele Hao

2 accepted papers

2017

Recurrent Ladder Networks

NeurIPS 2017poster

We propose a recurrent extension of the Ladder networks whose structure is motivated by the inference required in hierarchical latent variable models. We demonstrate that the recurrent Ladder is able to handle a wide variety of complex learning tasks that benefit from iterative inference and tempora…

Cited by 41SourcePDFScholar
2016

Tagger: Deep Unsupervised Perceptual Grouping

NeurIPS 2016poster

We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an unsupervised manner or alongside any supervised task. We enab…