UDC 004.89
TRAINING AND SELF-LEARNING IN A SELF-ORGANIZING INFORMATION SYSTEM
V. V. Drozhdin, PhD (in technical sciences), Associate Professor, Associate Professor at Department
of Information and Computing Systems, Penza State University, Penza, Russia;
orcid/0000-0003-2142-6521, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
This article examines the problem of high-level learning and self-organization of adaptive information
systems (AdIS) containing a formalized model of subject area in the form of a conceptual model. Currently, a
conceptual model is used only at system design stage and significantly less frequently (in sufficiently developed
systems) for solving data processing problems. Moreover, the adaptation of all information systems to
changes in subject area, user requirements, and internal organization is always performed by the developers
or system administrator (support group). However, the presence of a conceptual model in AdIS allows users
to create and maintain information systems adequate to changing subject area through high-level learning,
while self-learning and self-organization will ensure high efficiency and reliable operation of the system
over a long period. The aim of this work is to analyze and propose mechanisms for high-level learning and
self-learning of AdIS, which will allow the development of information systems based on the principles of
self-organization. Serious theoretical foundations for constructing AdIS with flexible structure and developing
self-learning and self-organization mechanisms are singled out: general systems theory, cybernetics,
synergetics, and logic. The proposed mechanisms of high-level learning through the creation and modification
by users of a conceptual model of subject area, self-organization of the system based on recording and
elimination of exceptions, identification of functional dependencies and generic relationships in database,
identification of hidden dependencies and generation of new concepts contribute to long-term effective functioning of ADIS in variable subject area.
Key words: adaptation, adaptive system, self-organizing information system, concept, conceptual model
of subject area, information system training, self-training of information system