Open AccessTHE PROBABILISTIC NEURAL NET NEURON’S NUMBER CALCULATIONS
Author(s) -
Galina Shcherbacova,
Victor Krylov,
Oleg Logvinov
Publication year - 2014
Publication title -
computing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.184
H-Index - 11
eISSN - 2312-5381
pISSN - 1727-6209
DOI - 10.47839/ijc.11.2.559
Subject(s) - artificial neural network , probabilistic logic , computer science , noise (video) , stability (learning theory) , probabilistic neural network , layer (electronics) , compact space , algorithm , artificial intelligence , pattern recognition (psychology) , mathematics , time delay neural network , machine learning , mathematical analysis , organic chemistry , image (mathematics) , chemistry
The sub-gradient method of estimation of the number of the hidden layer neurons of a probabilistic neural network is suggested. This method allows evaluating the data compactness violation in λ-space. This evaluation based on the noise stability sub-gradient iterative optimization method. This method allows reducing the number of the hidden layer neurons and classification time.