Abstract
In recent years Neural Networks or Neuromorphic Computing has significantly shifted the limits of what is computationally possible [1]. Recurrent Neural Networks are nonlinear dynamical systems, and as such they are inherently capable to process temporal information or signals. They show excellent performance in the prediction of chaotic trajectories or in the equalization of nonlinearly corrupted communication channels [2].
© 2019 IEEE
PDF ArticleMore Like This
Louis Andreoli, Sheler Maktoobi, Laurent Larger, Maxime Jacquot, Xavier Porte, and Daniel Brunner
NTh1A.2 Nonlinear Optics (NLO) 2019
Daniel Brunner, Maxime Jacquot, Ingo Fischer, and Laurent Larger
W2A.2 Latin America Optics and Photonics Conference (LAOP) 2018
Sheler Maktoobi, Louis Andreoli, Laurent Larger, Maxime Jacquot, and Daniel Brunner
W1D.4 Conference on Lasers and Electro-Optics/Pacific Rim (CLEO/PR) 2018