Authors

Using neural associative machines to detect intrusion into local networks

A MLP based algorithm for combining expert opinions using algorithmic composition with a dynamic mechanism to assess the coefficient of confidence in each expert is suggested. In order to increase the effectiveness of the experts the possibility of modifying the standard gradient algorithms learning methods based on the use of combined heuristics as well using experts in the Intrusion Detection System in the network is discussed.

Adaptive digital data flows router based on fuzzy neural network approach

Analysis of the data transmission channel characteristics using neural network

Security of information transmission over wireless communication channels based on neural network modules

Synchronization of communication nodes of the communication network on the basis of neural metanet

Adaptive control of frequency efficient data transmission system based on the neural network with optically-coupled elements

Optimal redistribution of radio frequencies based on reverberative spiking neuron networks interacted with communication electronics

Management of a multi-position system for identifying elements of adaptive transmitters based on hybrid data integration by a heterogeneous neural network

Control of distributed communication systems of information space-time duplication using neural networks of paired oscillators

The procedure for the synthesis of a neural network, which is based on a complex structure of paired neurons-oscillators that function in a certain topological map, is discussed. The use of neurons-oscillators with a variable activation threshold makes it possible to create reconfigurable neural memory circuits that act as a memory structure that can recreate the solution of a problem based on individual environmental signals. The use of mirror differential neurons that implement this principle of memory operation is proposed. This method of organizing a neural network makes it possible to implement an approach to neural network training that involves the reconfi ation of all variable parameters of neurons. Setting up individual cluster groups and their further interaction leads to the formation of a set of samples that correspond to the training sample. The use of interneuron switches, based on the use of an acoustic metamaterial, which properties can be changed by using electrocapillary phenomena, is reviewed. Switches are able to simultaneously accumulate multiple neural signals and then process them through an intermediate conversion into acoustic waves that propagate over the surface and through the volume of the metamaterial. Setting the parameters of switching elements using the optical diffusion tomography method makes it possible to create artificial neuristor lines and arrange signal processing in the interneuron space. The procedure for configuring and adapting the neural network architecture to solve the problem of increasing the reliability of transmitted information using the technology of multiple transmission of duplicate messages, is considered. Control of the method of access to the data transmission medium, as well as determination of the optimal number of frequency channels used, is carried out using the developed neural network of paired oscillators based on the analysis of the noise-signal environment. The effectiveness of the proposed neural network management is justified and the effectiveness of solving the task is evaluated. Read more...

Heterogeneous convolutional neural networks to build movement routes of the objects in spatial environment with accumulated energy potential

We consider the synthesis of a hybrid neural convolutional network with the modular topology-based architecture, which allows to arrange a parallel convolutional computing system to combine both the energy transfer and data processing, in order to simulate complex functions of natural biological neural populations. The system of interlayer neural commutation, based on the distributed resonance circuits with the layers of electromagnetic metamaterial between the inductive elements, is a base for simulation of the interaction between the astrocyte networks and the neural clusters responsible for information processing. Consequently, the data processing is considered both at the level of signal transmission through neural elements, and as interaction of artificial neurons and astrocytic networks ensuring their functioning. The resulting two-level neural system of data processing implements a set of measures to solve the issue based on the neural network committee. The specific arrangement of the neural network enables us to implement and configure the educational procedure using the properties absent in the neural networks consisting of neural populations only. The training of the convolutional network is based on a preliminary analysis of rhythmic activity, where artificial astrocytes play the main role of interneural switches. The analysis of the signals moving through the neural network enables us to adjust variable components to present information from training bunches in the available memory circuits in the most efficient way. Moreover, in the training process we observe the activity of neurons in various areas to evenly distribute the computational load on neural network modules to achieve maximum performance. The trained and formed convolutional network is used to solve the problem of determining the optimal path for the object moving due to the energy from the environment. Read more...

Synthesis of an optical neuromorphic structure with differentiated artificial neurons for information flow distribution

The work presents analysis of possible application of self-generating neural networks, which can independently generate a topological map of neuron connections while modelling biological neurogenesis, in multi-threaded information communication systems. A basic optical neural network cell is designed on the basis of the applied layered composition performing data processing. A map of neuron connections represents not an ordered structure providing a regular graph for exchange of information between neurons, but a set of cognitive reserve represented as an unconnected set of neuromorphic cells. Modelling of neuron death (apoptosis) and creation of dendrite-axon connections makes it possible to implement a stepwise neural network growth algorithm. Despite challenges in implementing this process, creating a growing network in an optical neural network framework solves the problem of initial forming of the neural network architecture, which greatly simplifies the learning process. Neural network cells used with the network growth algorithm resulted in neural network structures that use internal self-sustaining rhythmic activity to process information. This activity is a result of spontaneously formed closed neural circuits with common neurons among neuronal cells. Such organisation of recirculation memory leads to solutions with reference to such intra-network activity. As a result, response of the network is determined not only by stimuli, but also by the internal state of the network and its rhythmic activity. Network functioning is affected by internal rhythms, which depend on the information passing through the neuron clusters, which results in formation of a specific rhythmic memory. This can be used for tasks that require solutions to be worked out based on certain parameters, but they shall be unreproducible when the network is repeatedly stimulated by the same influences. Such tasks include ensuring information transmission security when using some set of carriers. The task of determining a number of frequencies and their frequency plan depends on external factors. To exclude possible repeating generation of the same carrier allocation, it is necessary to use networks of the configuration under consideration that can influence generation of solutions through the gathered experience. Read more...

Functional formation of a neuromorphic reservoir computational element based on a memristive metamaterial

A neural network structure is designed based on the ability of a certain class of calculators to recombine internal resources in order to produce neuromorphic elements to solve applied problems. This approach is rooted in a composite material with controlled local conductivity to form volumetric inhomogeneities capable of responding to and influencing external electrostatic effects. Such compounds aggregate into stable clusters suitable for modelling the processes that occur during information processing in natural neuronal entities. The use of conductive transitions between substrate-formed neuromorphic clusters as a learning structure makes it possible to increase the reliability of the neural network system. Long-term, non-volatile storage of information about the elements of the training sample in variable structures is possible. The basic approach to information conversion is to manage the electrostatic influence as it passes through the layered structures formed. The response to the input is not formed by propagating the signal through conductive elements with variable conductivity, but by passing the energy impact through a limited volume of metamaterial. Thus, a massively parallel processing of information can be achieved with the implementation of a mechanism for combining the opinions of independent neural network clusters that influence the final decision. Furthermore, this method of spreading effects in such an environment greatly simplifies the process of adding elements to the neural network. The lack of direct electrical interconnection facilitates the easy addition of new computational elements without significant rearrangement of the conductive media. Networks of this type are capable of significant growth without loss of experience. The input conversion process using modified delta coding prevents premature wear and tear on reconfigurable network elements. The manner in which information is presented and the manner in which neural network computing is organised enabled the creation of limited autonomous oscillations within the volume of the calculator to maintain circulating memory and the ability to gradually accumulate network experience for its subsequent recording in configurable elements. The identified features resulted in the application of this kind of calculators in the task of developing radio frequency management plans for the organisation of stable communication in a complex electromagnetic environment. Read more...

Neuromorphic electroactive macrocells for improvement of spatial orientation reliability

Neural network architecture based on polymer macrocells acting as neural elements and capable to generate electrically conductive synaptic junctions is developed. The architecture of a neural network processor where each component can record and produce a response to energy effects of different nature: electrical, optical and electrostatic has been developed. This function of the neural network eliminates the limitations related to the perception of the input information only by the input layer of the neural network processor. The impact of the influence of different input data representations on the information processing by the macrocell has been studied. The efficiency of temporal and electrical degradation of a neural network macrocell as a complex phenomenon directed on adaptation of a neural network to this process and generation of an algorithm for distribution of elements of a tutorial sample evenly over the total volume of available neural cells has been studied. The article studies a method of generation of episodic circulating memory, which significantly improves the speed of generation of a solution by the network, taking into account the gravitational interaction with macrocells. The revealed specific nature of the influence of the gravitational field on the functioning of neural network clusters was the basis for natural selection of cells by the performed properties depending on the spatial position in the neural network architecture. A method of exposure of the cell to physical equivalents of tutorial sample elements converted into different energy patterns to control the configuration of the macrocell using all available modes of information perception has been provided. Each exposure containing information on the tutorial element (optical and electrostatic) supports the generated generalising abilities of the neural macrocells composition. Practical significance of the performed research comprises the designed neural network system, which achieves an increase in performance due to self-organising oscillating neural clusters. The developed neural network model is used to reduce radio deviation and associated navigation errors due to conductive obstacles or atmospheric formations. Read more...