Towards generative design of computationally efficient mathematical models with evolutionary learning
In this paper, we describe the concept of generative design approach applied to the automated evolutionary learning of mathematical models in a computationally efficient way. To formalize the problems of models’ design and co-design, the generalized formulation of the modeling workflow is proposed. A parallelized evolutionary learning approach for the identification of model structure is described for the equation-based model and composite machine learning models. Moreover, the involvement of the performance models in the design process is analyzed. A set of experiments with various models and computational resources is conducted to verify different aspects of the proposed approach.
TY - JOUR
DO - 10.3390/e23010028
UR - http://dx.doi.org/10.3390/e23010028
TI - Towards Generative Design of Computationally Efficient Mathematical Models with Evolutionary Learning
T2 - Entropy
AU - Kalyuzhnaya, Anna V.
AU - Nikitin, Nikolay O.
AU - Hvatov, Alexander
AU - Maslyaev, Mikhail
AU - Yachmenkov, Mikhail
AU - Boukhanovsky, Alexander
PY - 2020
DA - 2020/12/27
PB - MDPI AG
SP - 28
IS - 1
VL - 23
SN - 1099-4300
ER -
@article{Kalyuzhnaya_2020,
doi = {10.3390/e23010028},
url = {https://doi.org/10.3390%2Fe23010028},
year = 2020,
month = {dec},
publisher = {{MDPI} {AG}},
volume = {23},
number = {1},
pages = {28},
author = {Anna V. Kalyuzhnaya and Nikolay O. Nikitin and Alexander Hvatov and Mikhail Maslyaev and Mikhail Yachmenkov and Alexander Boukhanovsky},
title = {Towards Generative Design of Computationally Efficient Mathematical Models with Evolutionary Learning},
journal = {Entropy}
}