The main task of the communication system is timely reliable and reliable transmission of messages between subscribers. In the event of interference, the communication system performs its task in accordance with the noise immunity it possesses. At the same time, the mixture of the useful signal, noise and interference, which comes to the receiver input, after the necessary processing, can serve as a source of information on the existing interference in the channel. Information on the presence and nature of interference thus obtained may be useful both for changing the parameters of the radio channel (modulation, frequency, mode) and for an external customer. This article is devoted to the use of neural networks to extract information from the damaged information signals about the nature of the interference that caused such damage.