Analytical and Numerical Study of Information Retrieval Method Based on Single-Layer Neural Network with Optimization of Computing Algorithm Performance

This work presents a mathematical model of a fast-acting single-layer artificial neural network applied to the task of image reconstruction after noise. For research purposes, this algorithm was implemented in the Python and C++ programming languages. The numerical simulation of the recovery efficiency of the described neural network was performed for different values of the noise factor, the number of samples required to train elements in the sample and the dimensionality of the coupling coefficients, w. The study of the mathematical model of this neural network is presented; as a result, it is possible to identify its essence, to reduce the number of operations required to recover a single element and to increase recovery accuracy by changing the order of calculation of coupling coefficients, w.

Automated summary

This work presents a mathematical model of a fast-acting single-layer artificial neural network used for image reconstruction after noise. The algorithm was implemented in Python and C++ for research purposes. Numerical simulation was conducted to study the recovery efficiency of the neural network for different noise factors, the number of samples required for training, and the dimensionality of the coupling coefficients, w. The study of the mathematical model of this neural network allows for identifying its essence, reducing the number of operations needed for recovering a single element, and improving recovery accuracy by changing the order of calculation of coupling coefficients, w.