Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Article

Download file Download BibTeX

Title

Regularization Theory in the Study of Generalization Ability of a Biological Neural Network Model

Authors

[ 1 ] Instytut Automatyki i Robotyki, Wydział Informatyki, Politechnika Poznańska | [ P ] employee

Scientific discipline (Law 2.0)

[2.2] Automation, electronics and electrical engineering

Year of publication

2019

Published in

Advances in Computational Mathematics

Journal year: 2019 | Journal volume: vol. 45 | Journal number: iss. 4

Article type

scientific article

Publication language

english

Keywords
EN
  • kinetic model of neuron
  • markov kinetic schemes
  • lagrange multipliers
  • generalization ability
  • Image processing
  • noise reduction
Abstract

EN This paper focuses on the generalization ability of a dendritic neuron model (a model of a simple neural network). The considered model is an extension of the Hodgkin-Huxley model. The Markov kinetic schemes have been used in the mathematical description of the model, while the Lagrange multipliers method has been applied to train the model. The generalization ability of the model is studied using a method known from the regularization theory, in which a regularizer is added to the neural network error function. The regularizers in the form of the sum of squared weights of the model (the penalty function), a linear differential operator related to the input-output mapping (the Tikhonov functional), and the square norm of the network curvature are applied in the study. The influence of the regularizers on the training process and its results are illustrated with the problem of noise reduction in images of electronic components. Several metrics are used to compare results obtained for different regularizers.

Date of online publication

04.01.2019

Pages (from - to)

1793 - 1805

DOI

10.1007/s10444-018-09658-6

URL

https://link.springer.com/article/10.1007/s10444-018-09658-6

Presented on

6th European Seminar on Computing, ESCO 2018, 3-8.06.2018, Pilsen, Czech Republic

License type

CC BY (attribution alone)

Open Access Mode

czasopismo hybrydowe

Open Access Text Version

final published version

Date of Open Access to the publication

at the time of publication

Full text of article

Download file

Access level to full text

public

Ministry points / journal

100

Ministry points / journal in years 2017-2021

100

Impact Factor

1,748

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.