The article presents a comprehensive approach to the development and optimization of a neural network model for effective face recognition in a dynamic environment. In particular, the neural network developed by the authors is considered, the purpose of which is to recognize a limited number of people. A training sample was formed to train the neural network. The paper describes the process of training a neural network using the Keras library, including the network architecture, layer sizes, activation functions and optimization methods. The stages of preprocessing and preparation of initial data for training a neural network are also discussed. The obtained research results show that the developed neural network has high performance and accuracy.