Using a neural network apparatus for study an adaptive learning trajectory

Keywords: neural network, adaptive learning trajectory, information quanta, learning algorithm, weights


A theoretical analysis of the current state of neural network technology was performed, which allowed us to identify the known algorithms for working with neural networks and figure out the advantages and disadvantages of their application to solve various scientific and technological problems. The relevance of the use of neural networks for the study of adaptive learning trajectories based on the analysis of current characteristics of the assimilation of information quanta by students, which ensures the successful conduct of distance learning using open communication platforms. The adaptive process of mastering new knowledge by the student of multilayer perceptron architecture is presented, in which each neuron is considered as a certain lesson, and the educational process is presented as the movement of the student in separate lessons. The application of the inverse error propagation algorithm and the least squares method has been implemented for network training. This made it possible to iteratively adjust the synaptic weights of each neuron by minimizing the network parameters based on minimizing the standard deviation between the correct and actual network responses. The general algorithm of adaptive training with use of a neural network is constructed and stages of its functioning are described. Prospects for further research aimed at applying modifications of the backpropagation algorithm and improving the selection of rules for correcting weights are identified.


S. Haykin, Neural networks, a comprehensive foundation. N.Y.: Macmillan College Publishing Company, 1994.

P. Gill, W. Murray, M. Wright, Practical Optimization. N.Y.: Academic Press, 1981.

A.Yu. Kononiuk, Neironi merezhi i henetychni alhorytmy. K.: «Korniichuk». 2008.

H. Szu, R. Hartley, Fast Simulated annealing. Physics Letters. Vol. 1222 (3, 4), pp. 157–162, 1987.

М. Pikuliak, "Development of an adaptive module of the distance education system based on a hybrid neuro-fuzzy network," Proceedings of the 2020 IEEE Third International Conference on Data Stream Mining&Processing (DSMP). Lviv, Ukraine, August 21-25, 2020, pp. 44-49.

«Artificial neural networks dlia vyrishennia biznes zadach». [Elektronnyi resurs]. Rezhym dostupu: Data zvernennia: 07.06.2022.

V.B. Nemirovskiy, A.K. Stoyanov, "Near-duplicate image recognition," Mechanical Engineering, Automation and Control Systems (MEACS): Proceedings of the International Conference, Tomsk, 2014.

S.O. Arik, J. Chen, K. Peng, W. Ping, Y. Zhou, "Neu-ralvoicecloning with a fewsamples. In Advances in Neural Information Processing Systems," Annual Conference on Neural In formation Processing Systems 2018, Neur IPS 2018. Montreal, Canada, 3-8 December 2018, pp. 10040–10050. 2018.

S.A. Krutyna, E.V. Malakhov, V.D. Hohunskyi, “Strukturuvannia znan u avtomatyzovanykh navchalnykh systemakh z elementamy shtuchnoho intelektu,” Modeliuvannia u prykl. nauk. doslidzhenniakh. Materialy XIV seminaru. Odesa: ONPU, 2007, s. 37-39.

M. L. Minsky, S. Papert, Perseptrons. Cambridge. MA: MIT Press, М: Мир. 1971.

K. Pal Sancar, Mitra Sushmita, “Multilayer Perceptron, Fuzzy Sets, and Classification,” IEEE Transactions on Neural Networks, Vol. 3, No. 5, pp. 683-696. 1992.

Abstract views: 0
PDF Downloads: 0
How to Cite
Pikuliak М., Savka І., & Dutchak М. (2022). Using a neural network apparatus for study an adaptive learning trajectory. COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (47), 91-97.
Computer science and computer engineering