Photo by sunburned_surveyor from unsplash
In this paper, we consider the problem of constructing a correction algorithm with the aim of increasing the adaptive properties of the ΣΠ-neuron, relying solely on the structure of the… Click to show full abstract
In this paper, we consider the problem of constructing a correction algorithm with the aim of increasing the adaptive properties of the ΣΠ-neuron, relying solely on the structure of the ΣΠ-neuron itself. To build the corrector, the logical-algebraic method of data analysis is used. Comparison of the advantages of the neural network approach and the logical-algebraic method suggests that a combined approach to the organization of the neural network improves its efficiency and allows one to build a set of rules that reveal hidden patterns in a given subject area, thus improving the quality of the recognition system.
Journal Title: Journal of Mathematical Sciences
Year Published: 2021
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!