Algorithm for a formation of a small training set using a multilayer perceptron for a priori estimates
https://doi.org/10.23947/2587-8999-2020-1-2-114-119
Abstract
The paper proposes an algorithm for the formation of a small training set, which ensures a reasonable quality of a surrogate machine learning model trained using this set. The algorithm uses multilayer perceptron to estimate heuristics and select the best next sample for the inclusion in a set. The paper tests the algorithm proposed applying it to the problem of deformation and breaking of a thin thread under the action of a transverse load pulse on it. The possibility to generalize the approach and apply it to building surrogate machine learning models for other physical problems is discussed.
Supporting agencies: The research is done within the frame of the independent R&D.
About the Author
M. Seleznov
Moscow Institute of Physics and Technology
Russian Federation
Russian Federation
Mykhailo Seleznov, Researcher
Institutskiy lane, 9, Dolgoprudny
References
1. Beklemysheva, K.A., Petrov, I.B. Damage modeling in hybrid composites subject to low-speed impact // Mathematical Models and Computer Simulations2019. – Vol. 11. – P. 469-478.
2. Kim, S.H., Boukouvala, F. Machine learning-based surrogate modeling for data-driven optimization: a comparison of subset selection for regression techniques // Optimization Letters. – 2020. – Vol. 14. – P. 989-1010.
3. Rakhmatulin Kh.A., Demianov Yu.A. Strength under high transient loads. – New York : Daniel Davey, 1966. — 348 p.
4. Vasyukov A.V., Elovenkova M.A., Petrov I.B. Modeling of thin fiber deformation and destruction under dynamic load // Matem. Mod. – 2020. – Vol. 32, iss. 5. – P. 95-102.
5. Hsiang-Fu Y., Fang-Lan H., Chih-Jen L. Dual coordinate descent methods for logistic regression and maximum entropy models // Machine Learning. – 2011. – Vol. 85. – P. 41-75.
6. Platt J. Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. In: Advances in Large Margin Classifiers // Cambridge : MIT Press, 1999. – P. 61-74.
7. Rumelhart D.E., Hinton G.E., Williams R.J. Learning internal representations by error propagation. In: Parallel distributed processing: Explorations in the microstructure of cognition // Cambridge : MIT Press, 1986. – P. 318-362.
Review
For citations:
Seleznov M. Algorithm for a formation of a small training set using a multilayer perceptron for a priori estimates. Computational Mathematics and Information Technologies. 2020;4(2):114-119. https://doi.org/10.23947/2587-8999-2020-1-2-114-119
Views:
327
Email this article 