Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Victor Arellano Quintana"'
Publikováno v:
Neurocomputing. 233:104-115
In this paper we present a Complex-Valued Recurrent Neural Network (CVRNN), trained with a recursive Levenberg-Marquardt (LM) learning algorithm in the complex domain, applying it to the problem of dynamic system identification, and to an adaptive ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3fb0a4a2da4d4a15157109eed006da1e
https://doi.org/10.1016/j.neucom.2016.09.109
https://doi.org/10.1016/j.neucom.2016.09.109
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319270593
MICAI (1)
MICAI (1)
The present article gives an extension of the real-valued recurrent neural network topology and its Back-Propagation (BP) learning to the complex-valued one. The BP learning is achieved by the use of diagrammatic rules to obtain the adjoint recurrent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::103f8f2a793fdf5fa20c0ac051ebc4e2
https://doi.org/10.1007/978-3-319-27060-9_27
https://doi.org/10.1007/978-3-319-27060-9_27
