Regularization Theory in the Study of Generalization Ability of a Biological Neural Network Model
[ 1 ] Instytut Automatyki i Robotyki, Wydział Informatyki, Politechnika Poznańska | [ P ] employee
2019
scientific article
english
- kinetic model of neuron
- markov kinetic schemes
- lagrange multipliers
- generalization ability
- Image processing
- noise reduction
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.
04.01.2019
1793 - 1805
CC BY (attribution alone)
czasopismo hybrydowe
final published version
at the time of publication
public
100
100
1,748