output
20022019
most citedLearning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

3.5k citations

Showing 2015Show all

8 papers · 1 filter

cs.CL20151.8k cited

Attention-Based Models for Speech Recognition

Jan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk +2

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation…

cs.LG2015125 cited

Blocks and Fuel: Frameworks for deep learning

Bart van Merriënboer, Dzmitry Bahdanau, Vincent Dumoulin +4

We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel. Blocks is based on Theano, a linear algebra compiler with CUDA-support. It facilitat…

physics.soc-ph20153 cited

Network heterogeneity and node capacity lead to heterogeneous scaling of fluctuations in random walks on graphs

Kosmas Kosmidis, Moritz Beber, Marc-Thorsten Hütt

Random walks are one of the best investigated dynamical processes on graphs. A particularly fascinating phenomenon is the scaling relationship of fluctuations with the average…

cs.IT201516 cited

Sampling of stochastic operators

Götz E. Pfander, Pavel Zheltov

We develop sampling methodology aimed at determining stochastic operators that satisfy a support size restriction on the autocorrelation of the operators stochastic spreading funct…

math.FA201517 cited

Identification of stochastic operators

Götz E. Pfander, Pavel Zheltov

Based on the here developed functional analytic machinery we extend the theory of operator sampling and identification to apply to operators with stochastic spreading functions. We…

math.FA20157 cited

Boundedness of Pseudo-Differential Operators on , Sobolev, and Modulation Spaces

Shahla Molahajloo, Götz E. Pfander

We introduce new classes of modulation spaces over phase space. By means of the Kohn-Nirenberg correspondence, these spaces induce norms on pseudo-differential operators that bound…