The questions related to the improvement of the performance of bithreshold classifiers are
treated in the paper. The new 4-layer neural network architecture is proposed whose first …

Packet routing in computer networks significantly affects the effectiveness of the network,
including its security. Various reasons can result in a certain router losing its trust from a …

We deal with theoretical issues concerning the application of the multithreshold architecture
in the theory of neural computation. The way of representing a multithreshold function by 2 …

Most of the modern mobile robotic platforms use interactive management using computing
and artificial intelligence technologies. A feature of mobile robotic platform is the ability to …

The accuracy of solving the approximation tasks in the case of analysis of large volumes of
tabular biomedical datasets by machine learning methods is not always high. This is …

We treat multithreshold neural units and propose the model of k-threshold multi-valued
neuron. The simple online learning algorithm is described, which is designed to train multi …

The task of improving classification accuracy in the case of analysis of short datasets is an
important problem, in particular, for express diagnostics in biomedicine. Hybrid methods …

The implementation of the base components of neuro-like cryptographic data protection
systems using FPGA is considered. The structure of the data encryption module using …

The model of the 3-layer feed-forward neural network is introduced whose first hidden layer
consists of bithreshold neurons and the other layers—of single-threshold ones. The …

The implementation of neuro-like data encryption using polynomials is considered. The
structure of the device was developed with the usage of the base operation of neuro-like …