Wyniki 1-1 spośród 1 dla zapytania: authorDesc:"Volodymyr V. PIVOSHENKO"

Low computational complexity algorithm for recognition highly corrupted QR codes based on Hamming-Lippmann neural network DOI:10.15199/48.2019.04.29

Czytaj za darmo! »

The beginning of the neural networks history is connected with the "connectionist models" or "parallel distributed processing", that are considered in the publication in 1943 of McCulloch and Pitts. These scientists proposed general approaches and specific mathematical models of the biological neural networks and their components - neurons, that became fundamental in the artificial neural networks theory. These neurons were presented as models of the biological neurons and as conceptual components for circuits, that performed computational tasks. They used threshold elements with two stable states, which are called “McCallock-Pitts neurons" [1]. The task of developing models and systems, which are based on the threshold elements was so unusual and complex, that only in 1956 was appeared the first capable artificial neural network - Rosenblatt perceptron. Its demonstrated the possibility of creating technical patterns, based on the models of the human brain, for image recognition. However, further researches of perceptrons showed, that their usage in the recognition systems is associated with many difficulties. In 1969 Minsky and Papert published their book, in which they described the deficiencies of the perceptron model and showed their fundamental nature. The negative prognosis of the authoritative scientists caused a decline in the interest in neural networks, which lasted more than ten years, but in the 80's after some important theoretical results, the neural networks began to rebound. The renewed interest is reflected in many researches, the amounts of funding, the number of conferences and journals associated with neural networks [2,3]. At the same time, neurocomputing begins to develop, which allows solving problems from different areas of knowledge using neural networks, which are modelled on ordinary computers [4]. The machine interpretation of the neural network came into the world of Computer[...]

 Strona 1