1 citations · 1 across the 3 of their papers we have counts for
5 papers · 1 filter
About rectified sigmoid function for enhancing the accuracy of Physics-Informed Neural Networks
Vasiliy A. Es'kin, Alexey O. Malkhanov, Mikhail E. Smorkalov
The article is devoted to the study of neural networks with one hidden layer and a modified activation function for solving physical problems. A rectified sigmoid activation functi…
Are Two Hidden Layers Still Enough for the Physics-Informed Neural Networks?
Vasiliy A. Es'kin, Alexey O. Malkhanov, Mikhail E. Smorkalov
The article discusses the development of various methods and techniques for initializing and training neural networks with a single hidden layer, as well as training a separable ph…
Separable Physics-Informed Neural Networks for the solution of elasticity problems
Vasiliy A. Es'kin, Danil V. Davydov, Julia V. Gur'eva +2
A method for solving elasticity problems based on separable physics-informed neural networks (SPINN) in conjunction with the deep energy method (DEM) is presented. Numerical experi…
Catenary and Mercator projection
Mikhail A. Akhukov, Vasiliy A. Es'kin, Mikhail E. Smorkalov
The Mercator projection is sometimes confused with another mapping technique, specifically the central cylindrical projection, which projects the Earth's surface onto a cylinder ta…
About optimal loss function for training physics-informed neural networks under respecting causality
Vasiliy A. Es'kin, Danil V. Davydov, Ekaterina D. Egorova +3
A method is presented that allows to reduce a problem described by differential equations with initial and boundary conditions to the problem described only by differential equatio…