Digital backpropagation gained popularity due to its ability to combat deterministic nonlinear effects. Starting from the maximum a posteriori criterion and building on tools from machine learning, we are able to additionally combat certain stochastic nonlinear effects
We introduce a novel training principle for probabilistic models that is an al-ternative to maximum ...
Several strategies for nonlinearity mitigation based on signal processing at the transmitter and/or ...
The performance of long-haul coherent optical systems is fundamentally limited by fiber nonlinearity...
We propose a maximum a posteriori-based scheme that extends digital backpropagation (DBP) by account...
Stochastic digital backpropagation (SDBP) is an extension of digital backpropagation (DBP) and is ba...
In this paper, we propose a novel detector for single-channel long-haul coherent optical communicati...
Despite of remarkable progress on deep learning, its hardware implementation beyond deep learning ac...
International audienceBackpropagating gradients through random variables is at the heart of numerous...
We present stochastic backpropagation, a novel maximum a posteriori detection method for coherent op...
International audienceBackpropagating gradients through random variables is at the heart of numerous...
This is the final version of the article. It first appeared from International Conference on Learnin...
This thesis is concerned with works in connection to double backpropagation, which is a phenomenon t...
We marry ideas from deep neural networks and approximate Bayesian inference to derive a gen-eralised...
Backpropagation is the algorithm for determining how a single training example would nudge the weigh...
We introduce a novel training principle for prob-abilistic models that is an alternative to max-imum...
We introduce a novel training principle for probabilistic models that is an al-ternative to maximum ...
Several strategies for nonlinearity mitigation based on signal processing at the transmitter and/or ...
The performance of long-haul coherent optical systems is fundamentally limited by fiber nonlinearity...
We propose a maximum a posteriori-based scheme that extends digital backpropagation (DBP) by account...
Stochastic digital backpropagation (SDBP) is an extension of digital backpropagation (DBP) and is ba...
In this paper, we propose a novel detector for single-channel long-haul coherent optical communicati...
Despite of remarkable progress on deep learning, its hardware implementation beyond deep learning ac...
International audienceBackpropagating gradients through random variables is at the heart of numerous...
We present stochastic backpropagation, a novel maximum a posteriori detection method for coherent op...
International audienceBackpropagating gradients through random variables is at the heart of numerous...
This is the final version of the article. It first appeared from International Conference on Learnin...
This thesis is concerned with works in connection to double backpropagation, which is a phenomenon t...
We marry ideas from deep neural networks and approximate Bayesian inference to derive a gen-eralised...
Backpropagation is the algorithm for determining how a single training example would nudge the weigh...
We introduce a novel training principle for prob-abilistic models that is an alternative to max-imum...
We introduce a novel training principle for probabilistic models that is an al-ternative to maximum ...
Several strategies for nonlinearity mitigation based on signal processing at the transmitter and/or ...
The performance of long-haul coherent optical systems is fundamentally limited by fiber nonlinearity...
DOI
Add to ORKG