View(s) :
4 (0 ULiège)
Download(s) :
0 (0 ULiège)
Abstract
We show that projectors proposed in the framework of Quantum Signal Processing can be implemented as Hamiltonian Neural Network based orthogonal filters. Moreover, such filters can be used as Universal Signal Processors. The structures of such processors rely on a family of Hurwitz-Radon matrices. To illustrate, we propose a procedure of nonlinear mapping synthesis. The problem of anticipation is reformulated as a problem of supervised learning.
Text
References
Bibliographical reference
Wieslaw Sienko and Wieslaw Citko, « Quantum Signal Processing via Hamiltonian Neural Networks », CASYS, 14 | 2004, 224-242.
Electronic reference
Wieslaw Sienko and Wieslaw Citko, « Quantum Signal Processing via Hamiltonian Neural Networks », CASYS [Online], 14 | 2004, Online since 08 October 2024, connection on 27 December 2024. URL : http://popups.uliege.be/3041-539x/index.php?id=2664
Authors
Wieslaw Sienko
Gdynia Maritime Academy 81-225 Gdynia, Morska 83, Poland
Wieslaw Citko
Gdynia Maritime Academy 81-225 Gdynia, Morska 83, Poland