About the effectiveness of evolutionary algorithms for multicriterial design of artificial neural networks

Artificial neural networks can be widely used in various fields: economics, medicine, space grown, etc. However, using neural networks to solve a particular problem arises the problem of choosing an effective structure of neural networks. Solving these problems is an important step in the application of neural network technology to practical problems, since these stages directly affects the quality (value) of the resulting neural network model. However, this takes more time and material resources, which leads to the need to automate the process. For this purpose the use of multicriteria evolutionary algorithms, such as SPEA, SPEA2 and NSGAII is offered as they can solve two problems at once. Firstly, they can generate a neural network, thus saving computational resources. And secondly, they can solve tasks quite efficiently. Modified evolutionary algorithms that produce selection of the most informative features, do not improve performance of algorithms that use all the inputs on the problems of small dimension, but significantly improve the accuracy, increasing dimension. The modified algorithms together with automatic design structure of artificial neural networks determine the most informative features, and include as inputs only weakly correlated with each other variables of the original problem.