Keyword: «artificial neural networks»

The authors show the features of the course "Essentials of artificial intelligence" for training bachelors of pedagogical education (profile – computer science). The authors describe the system of tasks for practical training of such topics, as "Neuron computer science", "Logical programming", "Functional programming", "Expert systems" and tasks for independent work of students.

Based on the analysis of theoretical material pattern recognition theory, the authors of the algorithm and software was created by performing a search, identification and grouping of text and graphic symbols on maps to solve the problem of building geographic information systems areas. To find the optimum detection method, a comparison was made of three basic methods: comparison matrix, selection of features and intelligent method of artificial neural networks; developed algorithms for pre-processing and post-processing. The best quality has shown the method of artificial neural networks, and it is recommended for character recognition in solving the problem.

The article presents the analysis of the learning of full-time study in the direction of "Economics" given individual characteristics that affect performance in the educational process. Regression analysis based on artificial neural networks

The paper presents a review of various methods and neural network algorithms for predicting spring flood hazards on the Lena River in the vicinity of Yakutsk. The factors that have a significant impact on the maximum level of floods are given, the combination of which can lead to catastrophic emergency situations. The risk of exceeding the water level in the flooding of the critical values in the Tabaga village area for the time period of 5, 10 and 77 years is assessed. A cartographic model of area zoning by degree of flood danger was built, areas of possible flooding of the area are shown.