Recommendation System for Material Scientists Based on Deep Learn Neural Network

The paper considers the possibilities of artificial neural networks and deep machine learning in the problem of predicting the physicomechanical properties of functional materials. It is shown that the popular deep neural network VGG with high accuracy solves the problem of hardness classification of metal alloy on the basis of iron. The prospects of building a generative adversarial network that is able to predict the structure of the alloy with pre-determined physicomechanical characteristics are discussed.