Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Srivallapanondh, Sasipim"'
Autor:
Srivallapanondh, Sasipim, Freire, Pedro J., Alam, Ashraful, Costa, Nelson, Spinnler, Bernhard, Napoli, Antonio, Sedov, Egor, Turitsyn, Sergei K., Prilepsky, Jaroslaw E.
For the first time, multi-task learning is proposed to improve the flexibility of NN-based equalizers in coherent systems. A "single" NN-based equalizer improves Q-factor by up to 4 dB compared to CDC, without re-training, even with variations in lau
Externí odkaz:
http://arxiv.org/abs/2307.05374
Autor:
Srivallapanondh, Sasipim, Freire, Pedro J., Napoli, Antonio, Turitsyn, Sergei K., Prilepsky, Jaroslaw E.
To reduce the complexity of the hardware implementation of neural network-based optical channel equalizers, we demonstrate that the performance of the biLSTM equalizer with approximated activation functions is close to that of the original model.
Externí odkaz:
http://arxiv.org/abs/2305.09495
Autor:
Freire, Pedro J., Srivallapanondh, Sasipim, Anderson, Michael, Spinnler, Bernhard, Bex, Thomas, Eriksson, Tobias A., Napoli, Antonio, Schairer, Wolfgang, Costa, Nelson, Blott, Michaela, Turitsyn, Sergei K., Prilepsky, Jaroslaw E.
In this work, we demonstrate the offline FPGA realization of both recurrent and feedforward neural network (NN)-based equalizers for nonlinearity compensation in coherent optical transmission systems. First, we present a realization pipeline showing
Externí odkaz:
http://arxiv.org/abs/2212.04703
Autor:
Srivallapanondh, Sasipim, Freire, Pedro J., Spinnler, Bernhard, Costa, Nelson, Napoli, Antonio, Turitsyn, Sergei K., Prilepsky, Jaroslaw E.
To circumvent the non-parallelizability of recurrent neural network-based equalizers, we propose knowledge distillation to recast the RNN into a parallelizable feedforward structure. The latter shows 38\% latency decrease, while impacting the Q-facto
Externí odkaz:
http://arxiv.org/abs/2212.04569
Autor:
Freire, Pedro, Srivallapanondh, Sasipim, Napoli, Antonio, Prilepsky, Jaroslaw E., Turitsyn, Sergei K.
In this paper, we provide a systematic approach for assessing and comparing the computational complexity of neural network layers in digital signal processing. We provide and link four software-to-hardware complexity measures, defining how the differ
Externí odkaz:
http://arxiv.org/abs/2206.12191
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Freire, Pedro J., Srivallapanondh, Sasipim, Napoli, Antonio, Prilepsky, Jaroslaw E., Turitsyn, Sergei K.
In this paper, we provide a systematic approach for assessing and comparing the computational complexity of neural network layers in digital signal processing. We provide and link four software-to-hardware complexity measures, defining how the differ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6fe4957d62985f47286c8313aa1615fd