Increase the speed of detection and recognition of computer attacks in combined diagonalized neural networks

In this paper, we propose a method increase the speed of detection and recognition of computer attacks using diagonalization matrices of synaptic connections in series-connected recirculating neural network and multilayer perceptron. It is established that the decrease in the number of weight of synaptic connections between neurons reduces the vulnerability of the combined neural networks of various computer attacks by about 10%. The main advantages of this approach is the ability of the combined diagonalized the neural network to reduce the time of adaptation to dynamic conditions and to increase the speed of its functioning in real time.