Dynamic Planning of Robot Behavior Based on an “Intellectual” Neuron Network
We examine the questions of applying large pyramidal neural (intellectual neuron) networks to solve equipment object control problems. We consider the description of a system for dynamic planning of mobile robot behavior, constructed based on a network of similar elements.
The article discusses development of the segmented characters classifier of the Russian alphabet and of the Arabic numerals on the basis of block neural network structures including the plurality of blocks for each individual character recognition and for the synthesis block decision.
The task of improving the quality of forecasting returns of financial instruments using multivariate mathematical models: regression models and neural networks was analyzed. To construct a multifactor model of returns used the assumption on the influence of market factors that have a different nature. A linear multivariable regression model was constructed using stepwise inclusion algorithm. The multilayer neural network trained using back-propagation algorithm. The quality of the neural prediction models forecast much higher quality, built with the help of a regression model.
In this paper, the main purpose is to consider applications of morphological analysis in text classifiation. Morphological analysis helps us to learn grammatical features of words, grammatical semantic and the interaction between the elements of text. We propose the neurosemantic network based on morphological analysis for learning vector representations of the text’s grammatical structures and the recursive autoencoder that consists of two parts - the fist part combines two vectors of words, the second one combines two vectors of morphology.
The purpose of this research is to develop a mechanism for forecasting foreign ex-change movements based on a combination of fundamental and technical approaches taking into account the speculative constituent in the pricing of a currency on the inter-national capital market. The significance of the work lies in the expansion of the practi-cal and theoretical aspects of foreign exchange rate forecasting, applying different types of analysis and in the formulation of recommendations for its most effective im-plementation. The research results may be used by bank foreign exchange departments, investment and other companies interested in trading on the international foreign ex-change market.
The mobile robots control subsystems are presented.