Structural Synthesis of Modular Weakly Connected Neural Networks. II. Nuclear Neural Networks

The simplest modular neural network is investigated, in which each module is a single-layer perceptron (a neural kernel). Numerical indices of quality by the criteria of operating speed and plasticity are proposed to characterize structural properties of nuclear neural networks. Based on the indices introduced, optimum procedures of structural synthesis are constructed.     

Structural Synthesis of Modular Weakly Connected Neural Networks. I. Methodology of Structural Synthesis of Modular Neural Networks

Structural models of modular neural networks without loops are considered. The notion of a weakly connected network is introduced. A genetic principle of generation of weakly connected neural networks is proposed, and its reproductive power is proved on the basis of the theory of categories. Algorithmic realizations of structural synthesis are considered. Some examples are given.     

CuO nanowhiskers: preparation,structure features,properties, and applications

This paper presents the results of a detailed study of the structure of nanowhiskers (NWs) of copper oxide formed in the process of thermal oxidation. It is shown that NWs have a bi- or poly-crystalline structure with a growth direction [110]. It is noted that the formation of NWs is facilitated by the cooperation of internal stresses with the defective structure of the underlying coating, and they grow owing to surface diffusion of copper cations from the depth of the coating to the top of the whisker. It is established that NWs have a good sorption and photocatalytic ability that will allow their use in the chemical industry, including the areas of catalysis and photocatalysis.     

Fractal learning of fast orthogonal neural networks

A new method of learning fast one- and multiple-dimensional orthogonal transformations is considered. Tunable orthogonal transformations are regarded as special neural networks. The learning takes a finite number of steps. The learning algorithm does not have the error feedback and is absolutely stable. The method is based on fractal filtering of signals and images. Linguistic models are used to determine the topology and structure of fast transformations. Examples are given.     

Structural synthesis of fast two-layer neural networks

Methods of construction of structural models of fast two-layer neural networks are considered. The methods are based on the criteria of minimum computing operations and maximum degrees of freedom. Optimal structural models of two-layer neural networks are constructed. Illustrative examples are given. Translated from Kibernetika i Sistemnyi Analiz, No. 4, pp. 47–56, July–August, 2000.     

Mathematical modeling and optimization of the monomerization stage of poly(ethylene terephthalate) production

Taking into account the presence of evaporable components in the reaction mixture, a mathematical model is suggested for the monomerization stage of poly(ethylene terephthalate) (PET) production. The model is analyzed by numerical methods. The problem of the monomerization-stage optimization is formulated as a multiobjective problem. An optimal profile of temperature for a cascade of reactors is calculated.     

Measurement of the moisture content of fiber in a layer of variable thickness

Conclusions The experiment showed that the joint use of two fundamentally different methods (in this case radioactive and capacitive) allows contactless measurement of the moisture content of wool and staple fiber in a layer of variable thickness; the root-mean-square error of measuring the moisture content of the fiber upon a change of the bulk thickness of the layer from 0.1 to 0.6 g/cm². was ±1%. The accuracy can be greatly improved by measuring the capacitance of the transducer at higher frequencies, 1.5–10 MHz. By using a comparatively simple computer the method permits automating the operation of the drier and obtaining information not only on the moisture content but also on the dry weight of the specimen. We can assume that (9) is applicable both for determining the moisture content of capillary-porous colloid materials in a layer of variable thickness (cloth, paper, cardboard, leather, food products) and for other cases where capacitive methods of measuring moisture content are used, but a change of the bulk thickness of the layer being monitored introduces substantial errors.Translated from Izmeritel'naya Tekhnika, No. 9, pp. 78–79, September, 1970.