Using generative neural networks when training digital engineers to improve the quality of their training

The problem and the aim of the study. Modernized higher education provides great prospects for artificial intelligence technologies to be introduced when training engineers for knowledge-intensive and high-tech industries. Applying generative neural networks makes it possible to meet the requirements both for programs to train relevant specialists and for the level of developed skills key to Industry 4.0 and for further Industry 5.0. The purpose of the study is to identify the possibilities of using generative neural networks when training digital engineers to improve the quality of their professional training. Research methods. The authors consider the generative neural network as an open resource with which it is possible to design, individualize and fill educational content in accordance with the professional interests of the participants in the interaction. The choice of service is justified by the type of information being processed and the engineer's work function being implemented. 68 bachelors of Vyatka State University are involved (Russian Federation). Training program: 08.03.01 – Construction. Focus: hydraulic engineering, industrial and civil engineering, Digital technologies for the examination of construction sites and real estate management. The assessment of the quality (level) of training is carried out with the help of materials from the fund of complex qualification tasks. For statistical processing of data, Pearson's chi-squared test is used. Results. The directions of work of students of the experimental group studying the discipline "Information Technology", including interactive communication supported by neural networks: generation of images and 3D-models, search for original titles, selection of a list of references, construction of diagrams and algorithms, etc. Statistically significant differences were revealed in the changes that occurred in the pedagogical system (χ2 = 9.095; p < 0.05). Conclusion. The summary are formulated that neural network services contribute to improving the quality of training due to the following didactic capabilities: presentation of information in various forms, automation of calculations, analysis of large amounts of data, decision support, etc. Difficulties are also highlighted: constantly updated features of services, the English-language interface, compliance with copyright and ethics of interaction on the network