Proceedings of the International Scientific Conference “Digitalization of Education: History, Trends and Prospects” (DETP 2020)

Using Neural Network Mathematical Models to Solve Pedagogical Problems

Authors
M.V. Lapenok, O.M. Patrusheva, S.A. Hudyakova
Corresponding Author
M.V. Lapenok
Available Online 13 May 2020.
DOI
https://doi.org/10.2991/assehr.k.200509.005How to use a DOI?
Keywords
artificial neural networks, intelligent systems, neural network mathematical modelling, pedagogical tasks
Abstract
This article describes the process of creating neural network mathematical models to solve such pedagogical problems as predicting the results of project activities of schoolchildren and developing recommendations for selecting a perspective project task; predicting student attendance based on their personal qualities, aims and lesson schedules; modelling the activities of student interns (musicians and future music teachers) related to their decision to attend theoretical classes, etc. The following stages of creating neural network forecasting systems are considered: formalization of the task, the formation of training examples, designing a neural network, its training and testing. To create neural network systems that implement mathematical models, special software was developed using a high-level cross-platform programming language Python.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Cite this article

TY  - CONF
AU  - M.V. Lapenok
AU  - O.M. Patrusheva
AU  - S.A. Hudyakova
PY  - 2020
DA  - 2020/05/13
TI  - Using Neural Network Mathematical Models to Solve Pedagogical Problems
BT  - International Scientific Conference “Digitalization of Education: History, Trends and Prospects” (DETP 2020)
PB  - Atlantis Press
SP  - 22
EP  - 26
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.200509.005
DO  - https://doi.org/10.2991/assehr.k.200509.005
ID  - Lapenok2020
ER  -