Reconstructed Brain Like Neural Network R-KFDNN

Through the neural system damage and repair process of human brain, we can construct the complex deep learning and training of the repair process such as the damage of brain like high-dimensional flexible neural network system or the local loss of data, so as to prevent the dimensional disaster caused by the local loss of high-dimensional data. How to recover and extract feature information when the damaged neural system (flexible neural network) has amnesia or local loss of stored information. Information extraction generally exists in the distribution table of the generation sequence of the key group of the higher dimension or the lower dimension to find the core data stored in the brain. The generation sequence of key group exists in a hidden time tangent cluster. Brain like slice data processing runs on different levels, different dimensions, different tangent clusters and cotangent clusters. The key group in the brain can be regarded as the distribution table of memory fragments. Memory parsing has mirror reflection and is accompanied by the loss of local random data. In the compact compressed time tangent cluster, it freely switches to the high-dimensional information field, and the parsed key is buried in the information.

Halanay inequality involving Caputo-Hadamard fractional derivative and application

A Halanay inequality with distributed delay of non-convolution type is considered. We establish a decay of solutions as a Mittag-Leffler function composed with a logarithmic function. A general sufficient condition is found and a large class of admissible retardation kernels is provided. This needs the preparation of several lemmas on properties of the Hadamard derivative and some basic fractional differential problems with this kind of derivative. The obtained result is then applied to a Hopfield neural network system to discuss its stability.

Neural Network Embedding of Functional Microconnectome.

Our brain works as a vast and complex network system. We need to compress the networks to extract simple principles of network patterns and interpret these paradigms to better comprehend their complexities. This study treats this simplification process using a two-step analysis of topological patterns of functional connectivities that were produced from electrical activities of ~1000 neurons from acute slices of mouse brains [Kajiwara et al. 2021] As the first step, we trained an artificial neural network system called neural network embedding (NNE) and automatically compressed the functional connectivities. As the second step, we widely compared the compressed features with 15 representative network metrics, having clear interpretations, including not only common metrics, such as centralities clusters and modules but also newly developed network metrics. The result demonstrates not only the fact that the newly developed network metrics could complementarily explain the features of what was compressed by the NNE method but was previously relatively hard to explain using common metrics such as hubs, clusters and communities. This NNE method surpasses the limitations of commonly used human-made metrics but also provides the possibility that recognizing our own limitations drives us to extend interpretable targets by developing new network metrics.

Reconstructed Brain Like Neural Network R-KFDNN

Through the neural system damage and repair process of human brain, we can construct the complex deep learning and training of the repair process such as the damage of brain like high-dimensional flexible neural network system or the local loss of data, so as to prevent the dimensional disaster caused by the local loss of high-dimensional data. How to recover and extract feature information when the damaged neural system (flexible neural network) has amnesia or local loss of stored information. Information extraction generally exists in the distribution table of the generation sequence of the key group of the higher dimension or the lower dimension to find the core data stored in the brain. The generation sequence of key group exists in a hidden time tangent cluster. Brain like slice data processing runs on different levels, different dimensions, different tangent clusters and cotangent clusters. The key group in the brain can be regarded as the distribution table of memory fragments. Memory parsing has mirror reflection and is accompanied by the loss of local random data. In the compact compressed time tangent cluster, it freely switches to the high-dimensional information field, and the parsed key is buried in the information.

Reconstructed Brain Like Neural Network R-KFDNN

Through the neural system damage and repair process of human brain, we can construct the complex deep learning and training of the repair process such as the damage of brain like high-dimensional flexible neural network system or the local loss of data, so as to prevent the dimensional disaster caused by the local loss of high-dimensional data. How to recover and extract feature information when the damaged neural system (flexible neural network) has amnesia or local loss of stored information. Information extraction generally exists in the distribution table of the generation sequence of the key group of the higher dimension or the lower dimension to find the core data stored in the brain. The generation sequence of key group exists in a hidden time tangent cluster. Brain like slice data processing runs on different levels, different dimensions, different tangent clusters and cotangent clusters. The key group in the brain can be regarded as the distribution table of memory fragments. Memory parsing has mirror reflection and is accompanied by the loss of local random data. In the compact compressed time tangent cluster, it freely switches to the high-dimensional information field, and the parsed key is buried in the information.

Research on Modeling and Dynamic Characteristics of Complex Biological Neural Network Model considering BP Neural Network Method

Biological neural network system is a complex nonlinear dynamic system, and research on its dynamics is an important topic at home and abroad. This paper briefly introduces the dynamic characteristics and influencing factors of the neural network system, including the effects of time delay and noise on neural network synchronization, synchronous transition, and stochastic resonance, and introduces the modeling of the neural network system. There are irregular mixing problems in the complex biological neural network system. The BP neural network algorithm can be used to solve more complex dynamic behaviors and can optimize the global search. In order to ensure that the neural network increases the biological characteristics, this paper adjusts the parameters of the BP neural network to receive EEG signals in different states. It can simulate different frequencies and types of brain waves, and it can also carry out a variety of simulations during the operation of the system. Finally, the experimental analysis shows that the complex biological neural network model proposed in this paper has good dynamic characteristics, and the application of this algorithm to data information processing, data encryption, and many other aspects has a bright prospect.

Mathematical models for evaluating the effectiveness of shock-absorbing fasteners of vibro-active mechanisms of marine objects by vibrational power

Для создания виброакустической защиты судового оборудования необходимо учитывать потоки колебательной энергии, распространяющиеся от источников как через опорные и неопорные связи, так и в виде воздушного шума. В работе представлены математические модели оценки эффективности амортизирующих креплений виброактивных механизмов морских объектов по колебательной мощности, учитываемые при обучении разрабатываемой нейросетевой системы классификации морских целей. Теоретические разработки в области виброзащиты и виброизоляции во многом имеют междисциплинарный характер и опираются на методы теории механизмов и машин, теоретической механики, теории колебаний, теории управления, используются методы инфорьт мационные технологии для оценки, поиска и выбора рациональных проектно-конструкторских решений. Создание амортизирующих устройств, способных защитить объекты от вибраций и ударов и, вместе с тем, обладающих ограниченными размерами, является сложной технической проблемой. В связи с этим первостепенное значение приобретают вопросы теории и расчета адаптивных виброзащитных систем. To create vibro-acoustic protection of ship equipment, it is necessary to take into account the flows of vibrational energy propagating from sources both through support and non-support connections, and in the form of air noise. The paper presents mathematical models for evaluating the effectiveness of shock-absorbing fasteners of vibro-active mechanisms of marine objects by vibrational power, which are taken into account when training the developed neural network system for classifying marine targets. Theoretical developments in the field of vibration protection and vibration isolation are largely interdisciplinary in nature and are based on the methods of the theory of mechanisms and machines, theoretical mechanics, vibration theory, control theory, information technology methods are used to evaluate, search and select rational design solutions. The creation of shock-absorbing devices that can protect objects from vibrations and shocks and, at the same time, have limited dimensions is a complex technical problem. In this regard, the issues of the theory and calculation of adaptive vibration protection systems are of paramount importance.

Fluoropolymer-based organic memristor with multifunctionality for flexible neural network system

In this study, we propose an effective strategy for achieving the flexible one organic transistor–one organic memristor (1T–1R) synapse using the multifunctional organic memristor. The dynamics of the conductive nanofilament (CF) in a hydrophobic fluoropolymer medium is explored and a hydrophobic fluoropolymer-based organic memristor is developed. The flexible 1T–1R synapse can be fabricated using the solution process because the hydrophobic fluorinated polymer layer is produced on the organic transistor without degradation of the underlying semiconductor. The developed flexible synapse exhibits multilevel conductance with high reliability and stability because of the fluoropolymer film, which acts as a medium for CF growth and an encapsulating layer for the organic transistor. Moreover, the synapse cell shows potential for high-density memory systems and practical neural networks. This effective concept for developing practical flexible neural networks would be a basic platform to realize the smart wearable electronics.

Modeling of the processes of extracting rules from Neural Network components with Petri nets

The paper deals with the use of extended Petri nets in modeling the processes of extracting rules from neural network components. The mathematical model for extracting rules from neural network components based on a modified timed Petri net is constructed, followed by an analysis of its dynamic behavior based on a timed reachability graph, which is a set of all its states that can be reached when a finite number of transitions are fired. The proposed model allows us to move from the initial detailed structure to its simplified description, which preserves the possibility of obtaining information about the structure and dynamic behavior of the neural network system. The proposed approach can be used in the synthesis of cognitive systems with a neural network organization to provide computational support for the functions of forming, learning, and correcting cognitive networks that display neural network models.

Improving the management of fuel combustion in ship boilers

Annotation – The article discusses the issues of increasing the efficiency of the combustion of liquid fuel in the furnaces of ship steam boilers using the proposed neural network system for automatic correction of the excess air coefficient. It is indicated that modern systems for automatic flame detection have a number of disadvantages, in particular, low sensitivity to extraneous illumination, etc. hot air or flue gases on the walls of the boiler furnace. Such pulsations reduce the reliability of the combustion monitoring and control system. Therefore, the task of developing and introducing on ships new, economically inexpensive and effective methods of effective control and management of the fuel combustion process in ship boilers using modern means of intelligent control is urgent. On the basis of the experiments carried out on a Mitsubishi MV 50 marine steam boiler and the collected experimental data, the values for training the neural network system of the air flow correction process, taking into account the color of the burner flame and the color of the flue gases, were obtained. The use of a trained neural network in the control system, taking into account the fuzzy expert system for monitoring the color of the flame and smoke, makes it possible to achieve the best excess air ratio depending on the steam load of the SEP units. Simulation modeling of the proposed neural system was carried out in a specialized program Matlab (Neural Networks Toolbox). The simulation results showed that the use of a neural network control system for the combustion of liquid fuel, using the example of a marine boiler, allows maintaining a given thermal regime over the entire range of steam load of the power plant units, and also allows timely correction of the excess air ratio, i.e. avoid excessive consumption of fuel.