116 citations · 289 across the 10 of their papers we have counts for
5 papers · 1 filter
A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
Marco Fraccaro, Simon Kamronn, Ulrich Paquet +1
This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non…
Hash Embeddings for Efficient Word Representations
Dan Svenstrup, Jonas Meinertz Hansen, Ole Winther
We present hash embeddings, an efficient method for representing words in a continuous vector form. A hash embedding may be seen as an interpolation between a standard word embeddi…
CloudScan - A configuration-free invoice analysis system using recurrent neural networks
Rasmus Berg Palm, Ole Winther, Florian Laws
We present CloudScan; an invoice analysis system that requires zero configuration or upfront annotation. In contrast to previous work, CloudScan does not rely on templates of invoi…
End-to-End Information Extraction without Token-Level Supervision
Rasmus Berg Palm, Dirk Hovy, Florian Laws +1
Most state-of-the-art information extraction approaches rely on token-level labels to find the areas of interest in text. Unfortunately, these labels are time-consuming and costly…
Dynamical Functional Theory for Compressed Sensing
Burak Çakmak, Manfred Opper, Ole Winther +1
We introduce a theoretical approach for designing generalizations of the approximate message passing (AMP) algorithm for compressed sensing which are valid for large observation ma…