Hamiltonian neural nets as a universal signal processor SIENKO, Wiesław. Politechnika Koszalińska - Wydział Elektroniki, Katedra Telekomunikacji 1993 - 2003 creator CITKO, Wiesław - doktorant. Politechnika Koszalińska - Wydział Elektroniki, Katedra Telekomunikacji text pl 2002 continuing eng
print
 This paper presents how to find an architecture for very large scale lossless neural nets, which can be used as Haar-Walsh spectrum analyzers. This analysis relies on the orthogonality of weight matrices W, where W could be Hurwitz-Radon matrices. The unique featrue of these nets is the possibility to treat them either as algorithms or as Hamiltonian physical objects (Haar-Walsh Signal Processors). Wiesław Sienko, Wiesław M. Citko. Dane z Informatora o publikowanych wynikach prac naukowo-badawczych w 2002 roku Wydziału Elektroniki. IEEE. - 2002 151211 20151211141608.0 BPP