In the article the features of construction of neural networks are studied, the main problems of neural networks are considered. To do this, the Android application was implemented and a series of experiments were conducted to identify the main features of neural networks. The following characteristics are assessed: the resources used to collect the project and the time it is debugged, productivity, and consumed resources. According to the results of the research the basic principles of the construction of specialized systems for working with neural networks have been formed. Artificial neural networks are computing systems inspired by the biological neural network sthat make up the animal brain. Such systems learn tasks (progressively improve their performance on them) by looking at examples, generally without special programming for the task. For example, in image recognition, they can learn to identify images that contain cats by analyzing sample images labeled "cat" and "cat", and using the results to identify cats in other images. They do this without any prior knowledge of cats, for example, that they have fur, tails, whiskers and cat-like squeaks. Instead, they develop their own set of relevant characteristics from the training material they process.