degann 0.2.4

Library for generating artificial neural networks for modeling the behavior of dynamic systems

DEGANN

DEGANN is a library generating neural networks for approximating solutions to differential equations. As a backend for working with neural networks, tensorflow is used, but with the ability to expand with your own tools.

Features

• Generation of neural networks by parameters.
• Construction of tables with the numerical solution of ordinary differential equations of the first order
• Construction of tables with numerical solution of systems of ordinary differential equations of the first order
• Choosing the Best Neural Network from Several for Fixed Training Parameters
• Iterating over training parameters with choosing the best neural network for each set
• Export neural networks as a function in c++
• Export Neural Networks as a Parameter Set
• Import Neural Networks from a Parameter Set
• Building a dataset with complete training results for approximating the solution of a differential equation for each neural network that participated in training