Abstract:
We analyzed the applicability of convolutional neural networks to solving the dataset fitting problem. The convolutional neural network was trained with training datasets containing function curves. We selected 6 linearizable functions. The convolutional neural network detected the functional relations in the datasets taken from the MNIST database intended for statistical software testing. The results show that it is possible to use the proposed approach for visual correlation analysis and curve-based data fitting.
Keywords:artificial neural networks, data fitting, convolutional neural networks, correlation analysis.
this study is a part of the GP 47 government order contracted to the Scientific Research Institute for System Analysis of the Russian Academy of Sciences, phase No. 0580-2021-0007 Advanced Simulation of Distributed Systems
Document Type:
Article
Language: Russian
Citation:
A. D. Smorodinov, T. V. Gavrilenko, A. A. Rassadin, “Applicability of convoluted neural networks to the dataset fitting problem”, Russian Journal of Cybernetics, 4:3 (2023), 47–54