DEVELOPMENT OF AN ALGORITHM FOR OPTIMIZING NEURAL NETWORK TRAINING WHEN DETERMINING THE NUMBER OF NEURONS IN A HIDDEN LAYER IN ORDER TO INCREASE THE PROBABILITY OF RECOGNIZING IMAGES OF A GROUND TARGET

Background. High accuracy of recognition of typical ground objects by optoelectronic tracking systems can be achieved by optimizing the parameters of an artificial neural network (INS) such as: the dimension and structure of the INS input signal, synapses of network neurons, the number of neurons of...

Celý popis

Podrobná bibliografie

Vydáno v:	Надежность и качество сложных систем číslo 4
Hlavní autoři:	Godunov, A.I., Shishkov, S.V., Balanyan, S.T., Al' Saftli, F.Kh
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Penza State University Publishing House 01.02.2022
Témata:	bayesian regularization algorithm goal hidden layer levenberg – marquardt algorithm neural network neural network training optimization probability recognition scalable conjugate gradient algorithm
ISSN:	2307-4205
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!