Serge Dolgikh

Work place: Department of Information Technology, National Aviation University, Kyiv, Ukraine



Research Interests: Computational Learning Theory


Mr. Serge Dolgikh holds the degrees of Distinction M.Sc. in Theoretical and Mathematical Physics from National Nuclear Research University (MEPhI) Moscow, Russian Federation and M.Sc. in Telecommunications Engineering, Coventry University, United Kingdom. He has a number of publications in Theoretical Physics, Information Theory research and technology applications and has worked on industry projects with leading network technology providers for over 15 years as an engineer and project manager. He currently works on several research projects in the areas of Unsupervised Learning and Self-learning Systems as well as international research funding initiatives with the Department of Information Technology, National Aviation University, Kyiv Ukraine and Solana Networks, Ottawa Canada.

Author Articles
Categorization in Unsupervised Generative Self-learning Systems

By Serge Dolgikh

DOI:, Pub. Date: 8 Jun. 2021

In this study the authors investigated the connections between the training processes of unsupervised neural network models with self-encoding and regeneration and the information structure in the representations created by such models. We propose theoretical arguments leading to conclusions, confirmed by previously published experimental results that unsupervised representations obtained under certain constraints in training compliant with Bayesian inference principle, favor configurations with better categorization of hidden concepts in the observable data. The results provide an important connection between training of unsupervised machine learning models and the structure of representations created by them and can be used in developing new methods and approaches in self-learning as well as provide insights into common principles underlying the emergence of intelligence in machine and biologic systems.

[...] Read more.
Other Articles