UDC 519.234
DOI: 10.36871/2618-9976.2021.12.004
Authors
Zvyagin L.S.
PhD of Economics, Associate Professor, Financial University under the Government of the Russian
Federation, Associate Professor of the Department "System analysis in economics", Moscow, Russia
Abstract
Artificial neural networks are currently an important extension
of the concept of computing. They have already made it possible
to cope with a number of difficult problems and promise the creation
of new programs and devices capable of solving problems
that are not yet humanly possible.
Today, many hopes for INS are associated with hardware implementations,
but so far the time for their mass market entry
has not yet come. They are either available as part of specialized
devices, or quite expensive, and often both. Considerable time
is spent on their development, during which the implementation
of software on the latest computers turns out to be an order
of magnitude less productive, which makes the use of neuroprocessors
unprofitable. However, the INS has a long way to go, comparable
to the same path that computers have recently taken.
Keywords
Neural networks
Modeling
Analysis
Processes and algorithms
Hardware implementation