Publication detail

Systems of Fragments of Artificial Neural Networks

SMETANA, B. CHVALINA, J.

Original Title

Systems of Fragments of Artificial Neural Networks

English Title

Systems of Fragments of Artificial Neural Networks

Type

conference paper

Language

en

Original Abstract

When we study structure of the most used artificial neural network - a multilayer perceptron and functionality of an artificial neuron, there is possibility using certain analogy with relations between descriptions of differential equations of a certain quality, in this paper is developed new approach to these subjects. In deeper View of point there can be used some concepts of locale finite trees of fragments of artificial neural networks and further to research by usage of monounary algebras and their characteristics with description and modeling systems of investigated structures of time—varying artificial neurons.

English abstract

When we study structure of the most used artificial neural network - a multilayer perceptron and functionality of an artificial neuron, there is possibility using certain analogy with relations between descriptions of differential equations of a certain quality, in this paper is developed new approach to these subjects. In deeper View of point there can be used some concepts of locale finite trees of fragments of artificial neural networks and further to research by usage of monounary algebras and their characteristics with description and modeling systems of investigated structures of time—varying artificial neurons.

Keywords

neural network, linear ordinary differential operators, groups of time-varying neurons, locally-finite trees

Released

04.02.2020

ISBN

978-80-227-4983-1

Book

19th Conference on Applied Mathematics Aplimat 2020 Proceedings

Edition

1

Edition number

1

Pages from

253

Pages to

270

Pages count

18

Documents

BibTex


@inproceedings{BUT162602,
  author="Bedřich {Smetana} and Jan {Chvalina}",
  title="Systems of Fragments of Artificial Neural Networks",
  annote="When we study structure of the most used artificial neural network - a multilayer perceptron and functionality of an artificial neuron, there is possibility using certain analogy with relations between descriptions of differential equations of a certain quality, in this paper is developed new approach to these subjects. In deeper View of point there can be used some concepts of locale finite trees of fragments of artificial neural networks and further to research by usage of monounary algebras and their characteristics with description and modeling systems of investigated structures of time—varying artificial neurons.",
  booktitle="	19th Conference on Applied Mathematics Aplimat 2020 Proceedings",
  chapter="162602",
  edition="1",
  howpublished="electronic, physical medium",
  year="2020",
  month="february",
  pages="253--270",
  type="conference paper"
}