Testing complex-valued perceptron properties experimentally

Autor:	S. A. Kirlan, V. M. Giniyatullin, A. V. Kirlan, E. I. Melnitskaya, R. M. Akhmetshin
Rok vydání:	2013
Předmět:	Sequence General Computer Science Delta rule business.industry Computer Science::Neural and Evolutionary Computation Xor problem Complex valued Artificial intelligence Electrical and Electronic Engineering Perceptron business Electronic Optical and Magnetic Materials Mathematics
Zdroj:	Optical Memory and Neural Networks. 22:65-71
ISSN:	1934-7898 1060-992X
Popis:	We have formed a sequence of steps for evaluating properties of chemical compounds. Our experiments have proved that complex-valued perceptrons can be used for predicting chemical properties. An algorithm has been developed to additionally train complex-valued perceptrons.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::d9aeef0177a5c4eeb5dc2e9e5df99ed3 https://doi.org/10.3103/s1060992x13010013 Zobrazit plný text záznamu Full text from SpringerLink