Evaluation of storage and functioning characteristics of artificial neural networks on the basis of a neurocomputer device

A solution to the problem of evaluating the temporal and quantitative characteristics of the storage and processing of artificial neural networks based on a neurocomputer device is proposed. The most popular and used topologies of artificial neural networks are considered, for which analytical relat...

Full description

Saved in:
Bibliographic Details
Published in:IOP conference series. Materials Science and Engineering 2020-01, Vol.734 (1), p.12009
Main Author: Romanchuk, V A
Format: Article
Language:English
Subjects:
Artificial neural networks
Neural networks
Topology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A solution to the problem of evaluating the temporal and quantitative characteristics of the storage and processing of artificial neural networks based on a neurocomputer device is proposed. The most popular and used topologies of artificial neural networks are considered, for which analytical relationships are presented that allow evaluating the training cycle of an artificial neural network, the amount of memory needed and the amount of transmitted data. The proposed relationships differ in that approaches and characteristics unique to neuroprocessor devices are offered for evaluation when implementing the calculations presented in the neural network logical basis.
ISSN:1757-8981
1757-899X
DOI:10.1088/1757-899X/734/1/012009