Skip to main content

InfoTech conference

2020 IEEE International Conference on Information Technologies

New Methods of Training Two-Layer Sigmoidal Neural Networks with Regularization

Vladimir Nikolaevich Krutikov
Guzel Sharipzhanovna Shkaberina
Mikhail Nikolaevich Zhalnin
Lev Alexandrovich Kazakovtsev
Reshetnev University, Krasnoyarsk
Russian Federation

In this paper we present an algorithm for training two-layer sigmoidal artificial neural networks (ANN) in the presence of significant interference and low-informative variables. Mixed smooth and non- smooth regularizing functionals are used to suppress the low –informative variables and to control interference. A computational experiment was organized comparing the quality of approximation by ANN models and logistic models with various types of regularization. The proposed algorithm for ANN learning in combination with non-smooth regularization allows us to obtain efficient ANN models for classification problems.

Key words:
machine learning