01180nab a2200205 i 4500001000400000003000400004005001700008008003900025040000800064041000800072100011300080245009900193260001000292500010700302520040600409700011000815773002300925942001300948999001300961BPPBPK20151211141608.0151211s2002    pl  |  |     |000 ||eng  cBPK  aeng  aSIENKO, Wiesław.d1993 - 2003.bPolitechnika Koszalińska - Wydział Elektroniki,cKatedra Telekomunikacji  aHamiltonian neural nets as a universal signal processor /cWiesław Sienko, Wiesław M. Citko.  c2002.  aDane z Informatora o publikowanych wynikach prac naukowo-badawczych w 2002 roku Wydziału Elektroniki.  aThis 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).  aCITKO, Wiesław - doktorant.bPolitechnika Koszalińska - Wydział Elektroniki,cKatedra Telekomunikacji  iW :tIEEE. -g2002  cART2UKD  c123d123