New method of training two-layer sigmoid neural networks using regularization

Autor:	Lev A. Kazakovtsev, Vladimir Kazakovtsev, Vladimir N. Krutikov, G. Sh Shkaberina
Rok vydání:	2019
Předmět:	Artificial neural network business.industry Computer science Two layer Pattern recognition Sigmoid function Artificial intelligence business Regularization (mathematics)
Zdroj:	IOP Conference Series: Materials Science and Engineering. 537:042055
ISSN:	1757-899X 1757-8981
DOI:	10.1088/1757-899x/537/4/042055
Popis:	We propose a complex learning algorithm for sigmoid Artificial Neural Networks (ANN). We introduce the concept of the working area of a neuron for sigmoid ANNs in the form of a band in the attribute space, its width and location associated with the center line of the band to a fixed point. We define of the centers and widths of the working areas of neurons by analogy to the radial ANNs. On this basis, an algorithm for selecting the initial approximation of network parameters, ensuring uniform coverage of the data area with neuron working areas was developed. Network learning is carried out using a non-smooth regularizer designed to smooth and remove non-informative neurons. The results of the computational experiment illustrate the efficiency of the proposed integrated approach.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::109fae23c36508be1b1e1307373d8863 https://doi.org/10.1088/1757-899x/537/4/042055 Zobrazit plný text záznamu