RU2680201C1 - Architecture for intellectual computing and information-measuring systems with fuzzy media computations - Google Patents

Abstract

SUBSTANCE: invention relates to the field of digital computing, intelligent computing systems and intelligent information-measuring equipment with stream processing of information in a fuzzy and intermittent computing environment and can be used both for creating intelligent virtual stream computing and information-measuring systems, the computing environment and information processes in which are caused by model and algorithmic closure, limitations of the physical environment, fuzzy and interleaved information environment, the exchange of energy and information, information uncertainty, and for the development and implementation of artificial intelligence systems. Method for constructing an intelligent stream computing and information-measuring system with a fuzzy computing environment based on an information model of an artificial neural network and a neuron and a flow model for obtaining results of calculations and measurements is: that the logical organization is implemented according to the principle of a multi-layer and multi-modular system, which includes a processor layer, a layer of modules for preparing input data streams and/or measurement streams as a logical data structure for corresponding streaming tasks, layers of active virtual memory for each processor element (PE) and groups of PE, layers of total active virtual memory.EFFECT: expanding the intellectual capabilities of computing and information-measuring systems, improving reliability and obtaining adequate results in conditions of isolation, limitations, exchange and uncertainty of a fuzzy computing environment.1 cl, 4 dwg

Description

The invention relates to the field of digital computing, intelligent computing systems and intelligent information technology with stream processing of information in a fuzzy and interleaved computing environment. It can be used both for the creation of intelligent virtual streaming computing and information-measuring systems, the computing environment and information processes in which are caused by model and algorithmic closure, limitations of the physical environment, fuzzy and interleaved information environment, energy and information exchange, information uncertainty, and for the development and implementation of artificial and computational intelligence systems, etc.

The closest logical, structural and technical solutions to the proposed are, on the one hand, the architecture for a box-based computing system (patent RU No. 2249854 of 04/10/2005), which refers to box-based software computing systems. From the point of view of architectural logical solutions, box-computing systems are fully functional, with unlimited use, Turing-complete computing systems that can perform, as the patent holder claims, any computing function, and computing capabilities lie in areas similar to the computing capabilities of living processing systems data. Such software computing systems are data processing systems that are logically organized in the system’s memory as a correlative object representing a point in private space, which is multidimensional and contains many points. A correlhythmic object is associated with each point through a metric and the data associated with this object is stored in memory. The processor-memory interaction uses a metric, which is a formula for calculating the value associated with the distance between the correlhythmic object and at least one point in space, for the correlative object and each of the many points in private space to form a set of values having a distribution with such an average value and standard deviation, that the ratio of mean to standard deviation increases with increasing dimension of the private space state.

The main and significant drawbacks of the indicated logical solutions, as the architecture of a software computing system, are the following: 1) as a data processing system, it does not in any way take into account their informational nature; 2) the indicated architecture, as a process, does not reflect the conditions of the flow of information processes of computational data processing technologies when they are implemented in a real logical and physical environment, namely: isolation (relative to memory elements and the information environment); conservatism or potentiality (as relatively limited hardware and software capabilities, energy-information exchange with an external real and virtual environment); information uncertainty - any interaction of two character chains fixed as a result generates information uncertainty.

On the other hand, reconfigurable multi-conveyor computing systems (RVS) for solving stream problems [1], which from the point of view of structural and technical solutions are an effective means for solving stream problems of information processing and control. In contrast to traditional multi-conveyor computing systems, the RCS allow creating virtual specialized multi-conveyor computers in the basic architecture of the FPGA field that are adequate to the network model of the streaming problem to be solved.

The main disadvantage of reconfigurable multi-conveyor computing systems from the point of view of both the logic of technologies for solving streaming information processing and control problems, and the construction of a network model of a streaming virtual computing system is the neglect of factors of fuzzy computing environment and the synergy of the principles of virtualization, intellectualization and parallelism in the architecture of a computing system for solving streaming tasks.

The technical result is the expansion of the functional and intellectual capabilities of computing and information-measuring systems, increasing the reliability of their information performance and obtaining adequate results in conditions of isolation, limitations, exchange and uncertainty of a fuzzy computing environment. An intelligent virtual streaming computing and / or information-measuring system with a fuzzy computing environment contains: a block of autonomously functioning processor elements (PE), the number of functioning PEs in a particular quantum of physical time is determined by the conditions of the computational process algorithm or its result from the previous time quantum; block of modules for preparing and generating a data stream (measurement results, input data, results of intermediate and final calculations) for stream processing and / or stream calculations; a block of two-level virtual active memory for each PE and a group of PEs; a block of shared virtual active memory available for all PEs; the information field of the coordinate systems of information binding and verification of the results (intermediate and final) of the computing process in the field of multi-level virtual active memory for each PE or group of PE; hardware-software interface for interfacing with the "outside world". Known varieties of architectures for streaming and multi-conveyor computing and information-measuring systems are based on linear models of algorithms and calculation or measurement procedures both in hardware implementation and in software without taking into account the facts of the influence of the physical and information environment of the formation and obtaining of results. In practical implementation, these models formalize three methods for obtaining the result, and therefore they represent three classes of models: 1) additive models for obtaining the result; 2) multiplicative models for obtaining the result; 3) additive multiplicative models for obtaining the result. The general principles for constructing functional and logical schemes for obtaining a result in such systems are based on the presentation of the result either as a sum of deterministic and random variables, or as a product of deterministic and random variables, or as a superposition of the first two. Algorithmic aspects of the implementation of the indicated models in the logic diagrams of the procedures for generating results and the computing environment of intelligent streaming computing and information-measuring systems manifest themselves identically within certain limits. In intelligent computing systems, the environment for computing and generating results has a more complex logical organization and mobility than the same environment for information-measuring systems. The functional and logical structure of the procedures and technologies for obtaining final results in the indicated systems does not allow taking into account such factors of the computing environment as the information dynamics of the data flow of computing processes and detection processes, the spatio-temporal scales of the physical environment, and the conditions of isolation, restrictions and exchange, information uncertainty and singular errors, virtualization and intellectualization, as well as much more.

It should be noted that the causes of errors caused by key quantities (accuracy and instability) of computational and information-measuring processes are based on the fact that the traditionally used computational and measurement technologies are very unstable. This instability is largely due to the fact that the technologies of computational and measuring processes of streaming and scalar computing are implemented without taking into account the information dynamics of objects in a fuzzy computing environment, which determines the occurrence of spatio-temporal and informational conditions for the controllability of computing processes.

The architectures and methods of organizing the new generation computing and information-measuring systems, which are currently being offered and will be implemented in the near future, indicate that the principles of parallelism, virtualization, and intellectualization, small spatio-temporal scales of the physical environment, conditions of isolation, restrictions, exchange, informational uncertainty of the computing environment are the determining and dominant circuitry and systemic factors in the development of designated tems. It should be noted that the information dynamics of computational and information-measuring processes in such systems will develop according to other physical and information laws and in other spatio-temporal scales, when spatial and dynamic factors of uncertainty (information, logical and physical), constraints (spatial, temporal and informational), exchange (energy and information), isolation (model and algorithmic). If the temporal evolution of the physical processes of streaming computations and measurements in such systems can be described by equations of quantum mechanics (such as Schrödinger equations) or of a similar type, then Boolean logic will have a different interpretation: blurred multi-valued logic, because due to the fact that information processes on the elements of the indicated systems proceed at nano-scales or less, the detection of the output state with a given measurement scale (this is the number of significant characters per unit of division and the relaxation time of the detector is several orders of magnitude longer than transients or phase transitions). And this means the following, that on a given scale for measuring or obtaining a calculation result and for a fixed relaxation time, within the framework of the currently available technical capabilities and the proposed solutions, this problem is really insoluble. The semantic content of this fact means that the selection of the stable state of such a logical nano-element of the system is an urgent problem both in the physical and technical aspects, as well as in the intellectual and informational, technological, computational and measuring. This fact is partially noted by the developers of such nano elements (the first copies of which were developed in Russia, MIET). Here we also need new mathematics both for describing flow processes at the physical level (apparently, the formalism of quantum mechanics is used in real elements) and for describing the dynamics of computational and information processes in the virtual environment of such systems.

The intellectual capabilities and intellectual effectiveness of the indicated systems as an intelligent tool in the technologies for organizing computational and information-measuring processes, simulation and information processing in order to achieve adequate, accurate and stable results when the diffusion of information is localized in spatio-temporal scales with blurred dynamics, were not considered and have not been investigated. Such questions are also open that are related to the development of information models for obtaining the final results of streaming calculations and measurements under conditions of model and algorithmic isolation, information exchange, limitations of the computing environment and information uncertainty. Modern advances in the relevant fields of natural science make it possible to assert with a high degree of certainty, on the one hand, that living intelligent systems process and analyze the flow of information in a fixed perception time quantum. And on the other hand, they realize their functions, including computational and information-measuring, in conditions of isolation (model and algorithmic), restrictions (spatial, temporal and informational), exchange (energy and information) and uncertainty (informational, logical and physical ) The indicated conditions for the functioning of living systems are also characteristic of intelligent computing and measuring systems, which are currently not implemented and are not described in any model for obtaining final results for existing systems of calculations and measurements (real and abstract).

The main objective of the present invention that we are introducing is to enable the development and implementation of the architecture (structure) of intelligent streaming computing and information-measuring systems with a fuzzy computing environment that overcomes the disadvantages of the prior art. As well as providing the possibility of developing and implementing a logical architecture (structure) for intelligent streaming computing and information-measuring systems with a fuzzy computing environment, the computational and information-measuring advantages of which lie in the fields of both intelligent measurement systems and information processing, and computational intelligence. Ensuring the possibility of implementing components of intelligent streaming computing and information-measuring systems with a fuzzy computing environment, bearing the advantages of a streaming information model of a neural network [2] in the technologies for obtaining the results of calculations or measurements as a unique mathematical, logical, information-measuring and computing structure, which the author of this inventions and which can be the fundamental and scientific basis for the implementation of virtual computing processes s intelligent stream computing simulation and information technologies of intelligent metering systems.

SUMMARY OF THE INVENTION

The author of the present invention found that the information model of an artificial neural network and neuron [2, 3], as a mathematical and logical prototype of an intelligent streaming computing and information-measuring system with a fuzzy computing environment, has important computational and informational properties of the mechanisms of computational and information-measuring processes and allows you to define and describe them taking into account mathematical, dynamic, informational and metrological aspects that are not obvious and support ALIVE new computing paradigm, measurement and implementation of non-traditional forms of computing based on information dynamics of objects blurred computing environment. This paradigm, on the one hand, has new computational and measuring advantages based on non-traditional principles of developing and implementing both streaming models for generating the results of calculations and measurements, and creating new forms of computing that allow us to synthesize the effects of parallelism, virtualization, and intellectualization on information dynamics fuzzy computing environment objects. On the other hand, it allows the synthesis of the influence of parallelism, virtualization and intellectualization mechanisms on the quality and reliability of obtaining the results of streaming calculations and measurements in a fuzzy computing environment.

The present invention discloses the architecture (structure) of an intelligent streaming computing and information-measuring system with a fuzzy environment, which allows to realize this new paradigm in the field of computational and artificial intelligence, as well as to access these new intelligent computing and information-measuring capabilities.

The objectives of the invention are achieved, on the one hand, on the basis of a method for constructing an intelligent virtual streaming computing system and / or information-measuring system with a fuzzy computing environment, according to which the processor modules, memory modules and data stream preparation modules of such a system logically, functionally and informationally interact by itself according to the same principles as neurons in a network information model of a neural network, determines its organization and implementation in the form of a multilayer and multi-modular parallel data processing systems where there are several layers, including a processor element (PE) layer, a data flow preparation layer, a two-level virtual RAM memory layer for each PE and a processor layer module, and a shared active virtual memory layer for the entire processor layer, the processor layer It is divided into virtual processor modules, and the layer of shared active virtual memory is divided into virtual memory modules, processor modules have a network model for organizing information links in perform the functions of the interface both between the elements of layers and with the external environment, initialize the computing system, route information in the system, configure the architecture of the virtual streaming computing system to the structure of the information graph of the problem to be solved, restore the results of the computing process when the entire system, individual layers, modules or elements, and the modules of the virtual RAM layer perform the functions of storing attributes of modules, commands, storage segments of the local coordinate system Information binding and verification of the results of (intermediate and final) computing processes in the computing environment [5], the modules of the total active virtual memory are functionally and logically designed to store a global information coordinate system for checking and verifying and displaying the results of the computing process on it at each step, It also performs buffer functions in tiling operations between layer modules, functions of virtual ports and information gateways with the outside world.

According to the indicated method, the processor modules are logically and functionally combined and configured into a virtual computing structure with the geometry and connection topology of the network information model of the neural network and each processor module operates in the corresponding area of the information space of the coordinate system for linking and checking the results, which ensures high reliability in the entire computing system and the reliability of the results, and the basic and forming elements of the module a virtual memory and a shared virtual active virtual memory cell are of two types: active and passive virtual cell. Logical and arithmetic operations in processor modules are implemented according to the following principles of computing: the principle of interaction of the operands of the computing environment with the information virtual environment [2, 3], the principle of virtual perspective in the design operator [4], the principle of the connection of the calculation results [5]: fractal and information .

And on the other hand, with the help of the structure of a virtual intelligent streaming computing and / or information-measuring system that implements a new paradigm of computational intelligence based on a network information model of a neural network [2]. The network information model of a neural network describes the structure (architecture) of an intelligent streaming computing and / or information-measuring system in the form of a global virtual information dynamic network in which the nature of the interaction between elements at the control and information exchange levels is defined as virtual processes with local virtual interaction. An element of such a network, a formal neuron, is defined as a local virtual computing system that combines the resources of processor elements and the memory of a real physical computing system with a rigid or reconfigurable (at the physical or virtual levels) architecture, the logical and physical functions of which are as follows. Firstly, it is a local virtual computer network that defines and sets in the physical environment of a real stream computing and / or information-measuring system a computer-measuring server-domain, i.e. the space of virtual identifier addresses for its processor elements and corresponding active memory segments. Secondly, the virtual computing and measuring server-domain defines not only the area of information definition in the space of virtual addresses of its active memory - its domain, but also defines the information boundaries of the address space of the memory domain as a general numerical scale for computational and / or information-measuring processes, and the price of division of the scale (numerical and informational accuracy) - its range. Elements of active memory are virtual cells of various types, differing in functional attribute, logical organization of information content. A neuron in the indicated architecture (structure) of a virtual intellectual streaming computing and / or information-measuring system is defined as its component, the purpose and function of which is as follows: 1) for a parallel streaming task, it implements it in a given area of possible values and a fixed quantum of physical time; 2) the implementation of statistical synchronization of the computational and / or information-measuring process in the neural network within the allocated real-time quantum. Neurons are combined into a virtual computational and / or information-measuring structure, which supports a computational and / or information-measuring process with a dynamically changing population of active neurons in a fixed and specific quantum of physical time. Active neurons can implement various computational and information-measuring processes within a specific quantum of physical time, if the interaction between them is parameterized by the task algorithm and the computing environment.

The neuron’s memory area is a local segment, the structural and logical organization of which is a model of active virtual memory [6] - passive cells (read-only), in which the coordinate information system of the fuzzy virtual computing environment is stored, and the active cells form the RAM of the processor elements. The geometric interpretation of the information coordinate system is that it determines the area of the segment’s memory that reflects the dynamics of the information processes of the fuzzy computing environment. The nodes of such a lattice in the broad sense are a figurative and symbolic reflection of the geometric and informational properties of the dynamics of processes of a fuzzy computing environment [4, 7]. The information essence of the geometry of nodes on the lattice defines it as a memory segment of virtual passive cells of a fixed length and with information unchanged in them, i.e. this is a segment of constants in the form of symbol chains. This part of the segment defines the domain for determining the display of the results of a computational and / or information-measuring process in the information space of the active virtual memory of the computing environment — their domain and range of values — range. The introduction of such a logical scheme as the organization of memory and the construction of an algorithm for a computational and / or information-measuring process defines computational and / or information-measuring systems with such an architecture as intelligent virtual stream computing-measuring systems with variable domain ranges. If the logic diagram of the computational process algorithm in a fuzzy neuron computing environment involves processes with local interaction, then interaction with other neurons of the neural network occurs. Computational processes in the indicated systems are quantized by physical time. The duration of the quanta can be arbitrary and is determined by the conditions of statistical synchronization and the computational process. In each quantum of physical time, the number of active neurons is determined by the result of calculations in the previous quantum and the conditions of the problem. Virtual cells of the active memory of a neuron that do not belong to the coordinate system of information binding and verification are active cells of variable length with dynamically changing information in them, i.e. these are working virtual cells. The process of interaction of character chains stored in passive and active virtual cells is defined as an information process with local interaction. Any operation between cells of different types is specified in the form of two operands - interaction and design. A more detailed meaningful description of such processes is reflected in the works of the inventor [3, 4, 5]. The indicated logical and algorithmic schemes allow you to build models of intelligent stream processing of information in a fuzzy computing environment.

It should be noted here that in the ontology of the subject area for the creation of designated computing and information-measuring systems, the flow of information or data in the meaningful and semantic aspects is logically and mathematically determined as follows. Firstly, in a fixed quantum of time of perception or detection (physical and informational), the duration of which for computing systems is determined by the number of operations at one step of the algorithm of the computing process, and for measuring (analog or discrete) - the duration of the physical processes of detection and relaxation, computing or measurement processes, a data stream is defined as a one-dimensional array or a linked list of data by which, on a scale of any nature (usually numerical), etsya finite set of quantum states calculated or measured values. Secondly, on an ordered set of designated time quanta, the flow of information or data is defined as a two-dimensional array or a similar list of data, and the rows of such arrays are one-dimensional flows of computation or measurement data for a particular time quantum. This is the difference between stream calculations or measurements from traditional ones, which in one step of the algorithm or time quantum only give one value of the result of a calculated or measured quantity, and in stream - a data stream. At the functional and logical level, algorithms and procedures for the synthesis, processing and analysis of data streams in such systems are formalized and described using the mathematical apparatus of stream models.

The architecture of intelligent streaming computing and information-measuring systems with a fuzzy computing environment (conditions of isolation, restrictions, exchange, small scales and information uncertainty) suggests that the hardware-software, computing, measuring and information-intellectual functions of such systems can actually be realized and implemented in the form of handware, software, brandware products (both individual platforms, and the synthesis of platforms of various levels in the form of circuit and system solutions). Such products make it possible to obtain more adequate, reliable and valuable data having an intelligent information coordinate system for linking and checking the results of calculations or measurements in a fuzzy (blurry) computing environment, based on the principles of locality (physical, informational, temporal and model) and setting the model of the informational environment formation of the result. The principles of locality determine the following important properties of the mechanism for obtaining results in various aspects, namely: 1) physical locality is due to limitations of a hardware-algorithmic nature; 2) temporal locality is due to quantization in physical time and algorithmic restrictions in information time; 3) the information locality or step of the information coordinate system is determined by the number of significant digits of the results obtained in the local range of values; 4) model locality is determined by the scope of the discrete linearized model for obtaining the results of calculations or measurements in the vicinity of nodes of the information coordinate system. The information environment model allows you to take into account the factors of uncertainty, limitations, exchange in the logic diagrams of algorithms and procedures for obtaining the results of calculations or measurements. In accordance with the present invention, the architecture (structure) of an intelligent streaming computing or information-measuring system with a fuzzy computing environment based on a streaming model of generating the result, may have a streaming computing system (e.g. transputer, FPGA fields, etc.) as a physical platform. or a multi-conveyor information-measuring system (with a rigid or reconfigurable architecture), as described above, includes blocks of processor elements, a block of preparation modules and the formation of data flows, blocks of active virtual memory of several levels, a hardware-software interface for interfacing with the "external" world. Such virtual computing or information-measuring systems support, on the one hand, three phases of virtualization - virtual space, image, and computing environment, and on the other - a dynamic model of the information environment for generating the result (computing environment). The practical consequences of using the architecture (structure) of intelligent streaming computing and information-measuring systems with a fuzzy computing environment mean that for many long unattainable and unknown properties and cognitive capabilities of intelligent systems for the synthesis, processing and analysis of information in conditions of isolation, limitation, exchange and information uncertainty physical environment become available ready-made. These properties and cognitive capabilities of the indicated systems include the ability, similar to living information systems, of creating new forms of intelligent streaming computing and measuring systems, new forms of reliability of their performance in conditions of isolation, limitation, exchange and uncertainty and a new class of computer computing systems. By implementing the new paradigm, the present invention not only provides computational and information-measuring advantages in the fields of computational intelligence and the implementation of new forms of obtaining results, but promises to generalize traditional computational and measuring science by moving to a different style of reasoning in terms of information dynamics and figurative representation of objects of information processes virtual and fuzzy environment for intelligent computing and measurement.

The conclusions are both having theoretical development and practical continuation with wide and far-reaching direct and immediate results. This architecture (structure), on the one hand, promises a direct breakthrough not only in the field of AI, computer and information-measuring sciences, but also in understanding the mechanisms of synthesis and intellectual processing of information in living systems. On the other hand, it promises significant new results in many other areas, including mathematics and computer science, psychology, and even sociology. A brief description of the drawings.

Fig. 1 is a schematic representation of an information model of a neural network as a mathematical and logical prototype of the architecture of an intelligent virtual streaming computing and information-measuring system

Fig. 2 is a geometric illustration of a multi-layer and multi-module implementation scheme of an intelligent virtual streaming computing and information-measuring system.

Fig. 3 is a schematic representation of a virtual memory model of an intelligent computing or information-measuring system in the form of a combination of subsets of active and passive cells.

Fig. 4 is a schematic drawing illustrating the operation of a design operator in a fuzzy computing environment.

To understand the essence and content of the present invention, it is necessary to identify and understand the important points of the physical, informational and logical-algorithmic functioning of intelligent streaming computing and information-measuring systems, which are manifested in the following. Firstly, the physical or dynamic functioning of such systems is closely related to the exchange of energy (momentum) between the elements of such systems and in the system as a whole. Secondly, the information functioning of such systems is associated with the exchange of information (symbols) between various elements (processor elements, elements of various types and fuzzy memory organization) of such systems. This type of functioning of computing and measuring systems is associated with virtualization processes, which are characterized by three phases of virtualization: virtual space, virtual image (image) and virtual environment. For example, performing the operation of multiplication (or multiple addition) in ALU, which is the basic element of the core of the processor element of computing or intelligent measuring systems, generates a virtual process that is characterized by three phases. What then is the source of such processes in the designated computing system (ALU and RAM)? First of all, it is a fixed (limited) bit depth of memory elements and ALU. Virtualization is generated in this case by limitations of a hardware-technical nature, and the result of which is the loss and diffusion of information on memory elements. On the other hand, hardware ALU generates and interprets the result based on the additive model, namely:

- алгоритмические переменные, т.е. те которым соответствуют элементы памяти; г^е _выч - результат вычислений, который определяется количеством значащих цифр и представляют информационную смесь скалярных величин x_n - полезное вычисление, h^e _n - информационная помеха, соответствующая е-му неизвестному варианту построения (e=1,D), ε _n - флуктуационный информационный шум, в реальных системах его источником являются так называемые ошибки округления.Where

- algorithmic variables, i.e. those which correspond to memory elements; g ^e _calcul - the result of calculations, which is determined by the number of significant digits and represent an informational mixture of scalar quantities x _n - a useful calculation, h ^e _n - informational interference corresponding to the e-th unknown construction option (e = 1, D), ε _n - fluctuation information noise, in real systems its source is the so-called rounding errors.

In the general case, the effect of information interference on the calculated or measured result can be expressed as the following operator V:

where x (t _n ) is a useful result, i.e. the exact value of the calculation result expressed in the number of significant digits; ε (t _n ) - stationary information interference, which is due to the model of the algorithm.

The following should be noted here: firstly, in algorithms such as iterative processes or that cannot be verified by direct substitution, there are informational interference of a different nature due to the dynamics of objects in the computing environment, and the nature of their mechanism of action is different. The effects of such interference in computing models in existing architectures of computing systems, as well as in hardware-algorithmic implementations of measuring systems, are uncontrollable, and the dynamics of their impact on the formation of the result of calculations is unknown. Secondly, the calculated results have neither the beginning of the information reference, nor the information binding system (not to be confused with the time and space bound ones - these are the computing and measuring systems).

с точки зрения вычислительного или измерительного процесса? Ответ: оно является в среде вычислений и среде формирования результата символическим обозначением модели следующего безконечного алгоритма:-

Но так как реализация таких алгоритмов в безконечных пространственно-временных масштабах вычислительно-измерительных систем теряет реальный смысл (абстрактный присутствует) обусловлена модельной замкнутостью, т.е. модель замыкается в данном случае количеством элементов в правой части уравнения. Аналогичную ситуацию имеем с вычислением или измерением элементарных функций типа: sin(t), exp (t), log (t) и т.п. и т.д. (если их разложить в ряд Тейлора - других способов для их вычислений не имеем). Для более сложных конструкций алгоритмов получаем замкнутость более грубую, что влияет на информационную динамику вычислительных процессов в виде информационной фильтрации или зашумления канала; 2) обмен информацией и энергией в вычислительных или измерительных процессах в информационном поле потока данных на элементах памяти (виртуальных и физических) в каналах передачи и хранения. Что это означает? А означает это следующее: происходит потеря и диффузия информации на элементах памяти, в результате влияния факторов цифровой фильтрации при выполнении операции и модельной замкнутости; 3) ограничения аппаратно-программных возможностей систем, которые влияют на структуру и характер протекания вычислительных или измерительных процессов, способы и возможности формирования среды вычислений; 4) информационная неопределенность проявляется в том, что объектами информационного взаимодействия вычислительных процессов, порождающих результаты (промежуточные и конечные), являются взаимодействующие цепочки символов, которые в свою очередь являются неоднородными объектами и порождают сложное информационное поле. Неоднократность взаимодействующих цепочек символов в вычислительных процессах на основе итерационных алгоритмов или рекурсивных схем проявляется достаточно широко. С одной стороны, в операциях (арифметических и логических) могут участвовать цепочки символов различной длины, а процессорный элемент «обрабатывает» цепочки фиксированной и равной длины (так как в реальности), что порождает информационные помехи, диффузию информации и ее виртуальный обмен с внешней средой. А с другой - после каждой бинарной операции между цепочками порождается деформированная (урезанная) цепочка и так процесс развивается на схеме нарастающего кома. Можно ли эти процессом управлять и контролировать его, как осуществлять информационную диагностику вычислительного процесса? В настоящее время контроль надежности и достоверности реализуемых алгоритмов в той или иной среде вычислений системы осуществляется с помощью числовых критериев, т.е. вычисляются или оцениваются числовые погрешности, которые используются в качестве критериев. Но такой подход никаким образом не отражает информационную сущность и динамику вычислительных процессов, а следовательно невозможно определить стратегию построения логических схем вычислительного процесса, которая позволяла бы с высокой степенью надежности и достоверности (с заданным количеством значащих в символьной цепочке результата) построить прогностический алгоритм процедуры получения результата и тем более получить оценки границы горизонта его прогноза (по шкале значений вычисляемой величины и по времени: физическому и информационному). Т.к. вычислительные процессы в среде вычислений реальных вычислительных или измерительных систем (любых: скалярных или потоковых) протекают в условиях модельной замкнутости и ограничениях, то в любом случае (даже если не присутствует априорная неопределенность исходных данных) порождает информационную неопределенность - это условия формирования нечеткой (размытой) среды вычислений.Thirdly, the computational and information processes that occur in a virtual environment simulating calculation or measurement algorithms are due to the influence of the following factors on their information dynamics: 1) model closure of the algorithms of “formation” (receipt) of calculation results; what is it and how is it manifested? For example, which means rationally a number

in terms of a computational or measurement process? Answer: it is in the computing environment and the environment of the result formation a symbolic designation of the model of the following infinite algorithm: -

But since the implementation of such algorithms on the infinite space-time scales of computing and measuring systems loses its real meaning (the abstract one is present) due to model isolation, i.e. the model is closed in this case by the number of elements on the right side of the equation. We have a similar situation with the calculation or measurement of elementary functions of the type: sin (t), exp (t), log (t), etc. etc. (if we expand them into a Taylor series - we have no other ways to calculate them). For more complex constructions of algorithms, we obtain a coarser closeness, which affects the information dynamics of computing processes in the form of information filtering or channel noise; 2) the exchange of information and energy in computing or measuring processes in the information field of the data stream on the memory elements (virtual and physical) in the transmission and storage channels. What does this mean? And this means the following: there is a loss and diffusion of information on the memory elements, as a result of the influence of digital filtering factors during the operation and model closure; 3) limitations of the hardware and software capabilities of systems that affect the structure and nature of the flow of computational or measurement processes, methods and possibilities of forming a computing environment; 4) information uncertainty is manifested in the fact that the objects of information interaction of computational processes that generate results (intermediate and final) are interacting chains of characters, which in turn are heterogeneous objects and generate a complex information field. The multiplicity of interacting chains of characters in computational processes based on iterative algorithms or recursive schemes is manifested quite widely. On the one hand, chains of characters of various lengths can participate in operations (arithmetic and logical), and the processor element “processes” chains of fixed and equal length (as in reality), which causes informational noise, diffusion of information and its virtual exchange with the external environment . And on the other hand, after each binary operation between the chains, a deformed (truncated) chain is generated and so the process develops on a growing coma diagram. Is it possible to manage and control these processes, how to carry out information diagnostics of the computational process? Currently, the reliability and reliability of the implemented algorithms in a particular computing environment of the system is controlled by numerical criteria, i.e. numerical errors are calculated or evaluated, which are used as criteria. But such an approach does not in any way reflect the information essence and dynamics of computational processes, and therefore it is impossible to determine a strategy for constructing logical circuits of a computational process that would allow constructing a predictive algorithm for the procedure for obtaining the result with a high degree of reliability and reliability (with a given number of significant values in the symbol chain of the result) and even more so, to obtain estimates of the horizon horizon of its forecast (on a scale of calculated values and in time: physical and inf rmatsionnomu). Because computing processes in the computing environment of real computing or measuring systems (any: scalar or stream) occur under conditions of model closure and limitations, then in any case (even if there is no a priori uncertainty of the source data) it generates information uncertainty - these are the conditions for the formation of fuzzy (blurred) computing environment.

The methodology of the present invention is based on an inductive method of developing intelligent virtual sweat (parallel) computing and information-measuring systems and information processing technologies and logic circuits for organizing computing and information-measuring processes. The nature of the dynamics of objects of information processes (these are processes with local interaction) in the indicated systems and technologies and the nature of their interaction in the computing environment are the dominant ideological factors in the way they are developed and implemented. Information objects in a virtual environment of streaming computing systems and technologies are interacting chains of characters (these are objects of non-numerical nature), and any formal object of a simulated procedure, operation or task in a computing environment is defined and described as the logical structure of such chains. The environment for the interaction of information objects of computing and information-measuring processes of designated computing systems and technologies includes the following main intermediary attributes: a virtual logical variable, interaction operators, a logical structure in the address space of the physically limited memory of the computing system, and others that are components of the computing environment. From an intuitive and logical point of view, the computing environment contains all or almost everything related to obtaining a result. All information objects of computational and information-measuring processes and the virtual computing environment in which the simulation and the process of obtaining the result are reflected and described based on the formalism of the information dynamics of the interacting chains of characters and the principles of constructing non-traditional computing and information-measuring technologies in a fuzzy computing environment: principle interaction of information objects and the principle of virtual perspectives [5, 7]. Everything that is done in a fuzzy computing environment is reduced to a certain fundamental principle: what is considered to be the identifier of a data stream or an individual element is taken and what is considered to be its value is constructed relative to the environment. Calculation or information detection is considered to be precisely this process of construction. The relationship between the identifier and its value is parameterized by the computing environment.

The main principles and principles of the approach under consideration for the methodology of creating both intelligent virtual streaming (parallel) computing and information-measuring systems with a fuzzy computing environment, as well as intelligent technologies for stream processing of information can be identified as follows: the basis of the approach in terms of the development and implementation of new forms computing and detection are the principles of interaction of information objects of the computing environment on quantum discrete information spaces and the principles of virtual perspective and the interaction of computing environment objects with the information environment of a computing and / or information-measuring system (active virtual memory). Within the framework of the indicated approach, the organization and implementation of computing suggests that the dynamic evolution of interacting symbolic chains in a computing and detection environment is determined on quantum discrete information spaces of the active memory of computing and information-measuring systems, a lot of interacting and evolving chains of characters in the cells of the address space of such memory, which is the physical medium of such interaction; they form a quantum discrete dynamo with the medium information system. In formalizing, interpreting, and implementing such a system, it is necessary to separate its dynamic, informational, mathematical, and metrological aspects [3, 5]. In reality, no information dynamic system, in particular a computing or information-measuring system, is closed and conservative, on the one hand, in the sense of activity and passivity of its processor elements and memory elements, and on the other, information dynamics in such information systems objects and the information environment is static and there is no way to implement information control, diagnostics and control of the computing process. The existing ideology of developing the implementation of computational and information-measuring systems (streaming and scalar) does not allow the implementation of new forms of computing and detection in the framework of the concept of closed potentiality. A new way is needed here (foundations, principles, formalism) - this is a rejection of the conditions of isolation and potentiality, i.e. transition to open dynamic information systems, in which the idea of the completeness of the information dynamics of computational and information-measuring processes is determined and made up of their dynamic elements and subsystems, as well as the nature of their interaction with the information environment. The considered and proposed method of creating both intelligent virtual streaming computing and information-measuring systems, and streaming information processing technologies offers a rejection of the principles of their information isolation and conservatism. The processor and memory elements of such systems are considered as multifunctional virtual streaming subsystems within the framework of its hardware-topological architecture, information-logical organization of the connections between elements and hardware-functional capabilities. Virtual information subsystems in the hardware-physical and information environment of such systems are both static and dynamic objects. The formation or generation of such subsystems is implemented at a logical level in the information environment of support systems (software systems and technologies) of the life of a real computing system.

The main advantages of the paradigm of quantum discrete information dynamic systems, as intelligent virtual streaming computing and information-measuring systems and new forms of implementation of computing and detection, are that they are from the standpoint of a single conceptual scheme and, in particular, a single mathematical, logical and algorithmic formalism allow you to naturally take into account the fundamental points that have introduced and are introducing into the theory of construction as intelligent streaming numeral and information-measuring systems, as well as streaming information processing technologies, the ideas of openness, locality, virtualization, quantum discrete spaces and information quanta. The fundamental points in constructing a methodology for creating intelligent virtual streaming computing and information-measuring systems based on the principles and approaches outlined above are the following main factors. First, the information dynamics of objects of computational and information-measuring processes cannot be closed and limited in the information space of the computing environment, nor can they be defined in the virtual information and address space of a real computing and information-measuring system (at the logical and virtual level), and only can be localized through the information quantum. Secondly, in the allocated (final) quantum of physical (or informational) time, the dynamics of objects of computational and information-measuring processes under conditions of physical isolation, limitations, exchange, and uncertainty have infinite informational evolution of possible quantum states that can be interpreted on an ordered set of time quanta as wave functions, i.e. vectors with unit norm.

Briefly summarizing the above, we can say that the existing methods for constructing intelligent streaming computing and information-measuring systems (scalar, streaming, and parallel) do not allow realizing at the logical and algorithmic level stream models for the synthesis of parallel schemes of computational and information-measuring processes even for non-branching regular iterative algorithms in the conditions of model closure, limitations of the computing environment, exchange and uncertainty. It should be noted that in this case, the synthesis of parallel flow diagrams of information processes includes not only the achievement of high reliability and adequate reflection of the results based on the methods of intelligent information processing, but also the intelligent computing environment and the generation of results using new forms of implementing intellectualization and virtualization technologies both memory and the information environment of processor elements.

The present invention is a new approach and a new paradigm for the synthesis of parallel circuits of computational and information-measuring processes and the construction of virtual streaming computing technologies for the implementation of streaming computing or algorithmic measurements in the conditions of model and algorithmic isolation, limitations, exchange and uncertainty, using stream models of information processes based on the information model of the neural network and neuron.

Multilayer modular scheme for implementing intelligent streaming computing and information-measuring systems with a fuzzy computing environment.

The physical, logical and virtual implementation of the architecture of an intelligent virtual streaming computing and / or information-measuring system based on the network information model of a neural network and a neuron is carried out according to the principle of a multilayer modular computing and information-measuring system. The organization of such a system includes several layers (see Fig. 2): a layer of processor elements (PE) (1st layer: No. 1), a layer of modules for preparing and generating input data streams (2nd layer: No. 2); layers of active virtual memory for each PE and a group of PE (2nd layer: No. 3), layers of total active virtual memory available for all PE (3rd layer: No. 4). Such a scheme for organizing a multilayer modular computing and information-measuring system can be implemented both on the physical and logical level, and on the virtual. The number of layers of such a system is determined by the geometry and topology of the neural network and the graph of the problem to be solved, the requirements for reliability of the result, the conditions for the organization of the computational and information-measuring process, etc. Each layer contains elements (physical and virtual) for the functional and logical purpose of one type for each layer (1 , 2, 3, 4). The interface between the elements of the first layer and layers with numbers Nos. 2, 3, 4 is organized at the logical and physical levels using inputs and outputs: 2nd layer - i | o1; 3rd layer - i | o3; 4th layer i | o4. The organization of the physical and logical interface between the elements of layer No. 2 with other computing and information-measuring systems is carried out through the inputs and outputs i | o2. The processor elements also perform the functions of an interface both between layer elements and with the external environment, initializing the computing system, routing information in the system, configuring the neural network topology as a logical image of the architecture of a virtual streaming computing system under the structure of the information graph of the problem to be solved, restoring the results of the computing process in case of failure the entire system, individual layers or elements. The processor layer No. 1 consists of processor elements (PE) with an arbitrary topology of links and an optionally unified logical pooling of interaction between them. In this case, PE is the functional module of the layer. The communication channels between them and bandwidth also need not necessarily be the same. Each PE has a two-level random access memory (OP). The set of OP blocks for each PE forms layer No. 3, i.e. OP blocks are memory layers.

The first level of the OP module (layer No. 3) is available only to a specific PE or PE module. The memory module of this level is divided into the following fields:

1st field is a field of attributes of PE, which are the following characteristics: 1) the logical number of PE is an information attribute by which the division number in the quantum scale for measuring the values of the calculated value is identified; 2) a sign and level of information activity of PEs, by means of which, during each allocated quantum of physical time of streaming processing, new PEs can turn on and their activity level is estimated; attributes of communication with memory of lower levels;

2nd field is a command memory field;

3rd field - the field of active basic virtual memory, which is divided into passive virtual cells of arbitrary fixed length, unchanged during the computational process, and the information in them also does not change. This field is that area of memory (inaccessible for writing) in which the local coordinate system of information binding and verification of the results (intermediate and final) of computing processes in the environment of PE calculations is stored (see Fig. 3). The coordinate information system, in turn, is a global information attribute, through which it is specified to define the mapping of the states of the dynamic evolution of computing process objects in the information space of active memory — their domain — and their range of values — their range.

The second level of memory in its organization (logical, virtual and informational) with priority access to the fields of this level by various PEs has the following features. First, the fields of this level form a dynamically active virtual memory, the logical organization elements of which are two types of virtual cells: 1) active cells, the dimension of which and the information in them change; 2) active-passive cells, their dimension changes, but not semantic information. Secondly, this memory level is logically divided: into fields accessible to a specific PE and into fields available to other PEs of an intelligent streaming computing and information-measuring system.

The fields available to a particular PE are subsets of virtual addresses for various types of virtual cells in real physical memory. The logical structure of the organization of these fields in computational processes is dynamically changeable. The mechanism for implementing a dynamic variable logical structure of such fields in the address space of virtual cells of various types of a limited area of the real physical memory space of a computing and information-measuring system is simple enough to implement various forms of computing and is not tied to either data types or addressing systems. In this case, the contents of the virtual cell are interpreted as a binary field (set), and the addresses of virtual cells (the logical structure of the address space) can change after each operation or their combination. These fields also form a virtual address space for working cells and storing intermediate results of a particular PE.

The fourth layer No. 4 forms the space of the total active virtual memory in the address and information space of the real physical memory of the computing and / or information-measuring system. This layer is logically divided into memory modules, which are used to implement the following goals.

First, a logical structure of virtual memory is formed on the selected subset of modules, which reflects the coordinate lattice of the information system of coordinates for checking and verifying the results of the computational process, the nodes of which correspond to passive virtual cells [4, 8]. The results of calculations (intermediate and final) or measurements in successive time quanta into which computational and measuring processes are divided are stored in passive memory cells of the coordinate lattice and form a logical raster structure for the reflection of the results in the form of symbolic chains for values of a discrete blurred random function. The logical structure of the results at the nodes of the lattice is an information display of the final topology of the image of the results of either the computing process or the information-measuring process (it should be noted that in intelligent systems these processes are interconnected) by layers.

Secondly, the modules of layer No. 4 perform buffer functions in tiling operations between the modules of layers, the functions of virtual ports and information gateways with the outside world, of a simulated task or of a computing process by layers. Secondly, the modules of layer No. 4 perform buffer functions in tiling operations between layer modules, the functions of virtual ports and information gateways with the outside world.

The second layer No. 2 forms a plurality of modules for preparing input data streams and / or measurement streams in the form of a logical data structure for the corresponding stream tasks, which are logically and functionally combined and configured into a local virtual stream computational structure with the geometry and topology of connections of the network information model of the neural network. The interaction and interface between the modules of this layer and the modules of other layers at the physical and logical levels is organized using the inputs and outputs i | o1, and with other computing and information-measuring systems of the “outside world” it is carried out through the inputs and outputs i | o2. The modules of layer No. 4 perform buffer functions in operations between the modules of layer No. 1, the functions of virtual ports and information gateways both with modules of other layers and with the "outside world".

Organization of computational and information-measuring processes in intelligent streaming computing and information-measuring systems with a fuzzy computing environment

Intelligent streaming computing and information-measuring systems based on the network information model of the neural network and neuron are universal new-generation intelligent systems with new capabilities. In this section, the author of the invention confirms this statement and describes a logical configuration diagram of the architecture of an intelligent virtual streaming computing and information-measuring system with a fuzzy computing environment according to the geometry and topology of an artificial neural network under the structure of the information graph of the streaming task.

The fundamental unit of a virtual streaming computing system is a neuron (see Fig. 1). The physical prototype of a neuron in the processor layer No. 1 of the computing and information-measuring system is the union of a certain amount of PE (1), and in layer No. 3 it is the union of the corresponding memory modules (3). The number of PEs in a neuron is determined by the functional purpose and logical organization of the computing process according to the structure of the information graph of the streaming task. The organization of information input and output connections for various types of buses between the modules of layers No. 1, No. 3, No. 4 within the boundaries of the information space of both neural and neuron is carried out at the inputs and outputs i | o1, i | o3, i | o4 of a multilayer modular scheme computing system. PEs perform arithmetic and logical operations on symbolic chains of variable and fixed lengths, which are stored in the active virtual memory of module 3. In layer 2, combining a certain number of modules for preparing input data streams or measurement streams is both a physical and virtual prototype of a neuron.

Because Since computational and information-measuring processes in the virtual environment of an intelligent streaming computing system are implemented and proceed under conditions of model and algorithmic isolation, restrictions, exchange, and uncertainty, models of algorithms and procedures in a fuzzy computing environment are constructed using stochastic Monte Carlo-type schemes. Algorithms of stream calculations constructed by such schemes belong to the class of algorithms on fuzzy subsets, and the results of calculations based on such algorithms are smeared stochastic quantities whose values (symbol chains of a fixed length) are determined at the nodes of the lattice of the information coordinate system, the physical environment of which is the set passive virtual cells of active virtual memory. The logical scheme for constructing stream calculations or algorithmic measurements such as iterative processes, the accuracy of calculations and the effectiveness of which cannot be verified by direct substitution or in other ways, based on vague algorithms of operations and procedures can be described as follows. The accuracy of the information representation of the source data or measurement data, operands of operations and the results obtained in a fuzzy computing environment of any computing system in the form of a character chain is specified by the number of significant characters. In order to ensure the required accuracy specified by the number of significant characters, over the entire interval of such an iterative computational process, it is necessary that the length of the symbol chains of the operands of logical or arithmetic operations be much greater than the required accuracy. In this case, chains of different lengths participate in the operations. Therefore, at the beginning of the main operation, as described above (the dynamics of such computational processes are described in more detail in the works of the author of the invention [3, 4, 5, 7, 8]), the operation of interaction with the information environment is implemented, and then a specific logical or arithmetic operation is performed . It should be especially noted that in a fuzzy computing environment of intelligent streaming virtual computing and information-measuring systems, the difference between the concepts of a calculated or measured quantity and a calculated or measured quantity is strictly defined and indicated, which consists in the fact that the calculated or measured quantity is a determined quantity, and a calculated or measured value is a fuzzy (blurry) value, the information image of which (a character chain of a fixed length) is determined tsya on lattice sites information system of coordinates. After the interaction operation between operands is completed, the operation of designing the result of the previous operation to the lattice node of the coordinate information system is performed. The initial conditions of the indicated iterative process are determined and set in the information neighborhood of one or more nodes of the lattice of the information coordinate system. The lattice of the coordinate information system is logically divided into layers of possible values (domain of definition) of the result of the calculations, interconnected in time or in a parametric variable, i.e. Each neuron or module has its own domain-range in the value space of the general scale of the information coordinate system. The time interval (physical or informational) of the implementation of the computing process is a multiple of the physical quanta of time of a fixed duration. In the selected quantum of physical time, only information objects of neighboring layers interact. It should also be noted that the lattice of the information coordinate system has a geometry similar to a neural network. In each quantum of physical time in a fuzzy computing environment, the number of active neurons is fixed and determined, but after the calculations are completed in a specific fixed time quantum, their number in the next quantum step can change quantitatively and qualitatively, when new neurons can be connected to calculations or algorithmic measurements. This is due to the fact that during informational interaction of the results of calculations with symbolic chains at the lattice nodes of the information coordinate system, they can fall into the information zone of inactive neurons and then such a neuron is activated in the next quantum step. When organizing a computing process in a fuzzy computing environment of a computing and / or information-measuring system having the architecture of an information model of a neural network, the coordinate lattice of the information-binding and verification system of the calculation results is logically and informationally divided into parts and each neuron functions in the corresponding area of the information space of the coordinate lattice . After completion of the computational or information-measuring process, i.e. the mechanism of designing the flow to the lattice of the information coordinate system is implemented (see Fig. 4), we obtain a blurred image of the image of the calculation result in the form of a topological complex on the set of active nodes, the values of which are reflected in the set of passive virtual cells of virtual active memory. Next, the procedure for extracting from a blurred image the result of calculating a deterministic image of the result is implemented. To implement this procedure, the operation of topological incarnation of a blurred image of the result is carried out, which takes into account the criteria for the connectedness of the calculation results: fractal connectedness and informational connectedness [5]. The adequacy of the result is determined by the degree of proximity of the estimates of the result obtained according to the specified criteria.

The fact that intelligent virtual streaming computing and information-measuring systems based on the information model of the neural network and neuron are really effective and new is not emulation or synthesis of computing and information-measuring technologies in a fuzzy computing environment of traditional computers, but emulation and synthesis technologies of intellectual information processing in perception systems of living systems. For example, the eye of a living system detects and processes information based on the following operations: interaction and projection into the nodes of the fundus lattice. The ear processes information in the same way. The unique and sustainable nature of the information model of the neural network and its elements determines and reflects its analogue in the architecture of the corresponding intelligent virtual streaming computing and information-measuring systems, which creates wide opportunities for the development of artificial and computational intelligence systems, a wide range of logical and software designers related to the implementation sphere solutions in the field of artificial intelligence and pattern recognition, through the fact that they allow the implementation of new The principles of computing in a fuzzy environment of intelligent streaming computing and information-measuring systems.

An additional advantage of intelligent virtual streaming computing and information-measuring systems is, on the one hand, a unique form of parallel streaming information processing and organization of parallel streaming computing and information-measuring processes. Since all neurons of a neural network form local dynamic computational and / or information-measuring networks that are autonomous within a quantum-step of calculations or measurements, even for processes combined by one algorithm or measurement model, they allow the use of a neural network with its geometry and connection topology as a template -environment in which neurons can simultaneously participate in solving various streaming tasks and implementing a wide range of logic circuits. And on the other hand, layer 2 neurons implement information technology for synthesizing and structuring the data stream, i.e. essentially function as a neural network processor for synthesizing an input data stream or a measurement stream.

Conclusions, consequences and scope of the invention.

Thus, the described network information model of the neural network, the streaming model of obtaining the results of calculations and measurements, and the theory of processes with local information interaction of fuzzy objects and the virtual environment for generating results in it show the practical nature of the present invention. New entity-objects were described: a network information model of a neural network and a neuron, a streaming model of obtaining an information result in the form of a data stream, an active virtual memory model, passive and active virtual memory cells, a modular and multilayer implementation scheme for the indicated computational and information-measuring systems with fuzzy computing environment, stream processes with local information interaction, stream interaction and design operators, information coordinate system formation of the result. Each of these entity-objects is an architecture or its element for a system that can be broadly defined as an intelligent virtual streaming computing or information-measuring system with a fuzzy computing environment based on a network information model of a neural network and a neuron and a streaming model for obtaining the result in fuzzy computing environment, which is the object of the present invention. The formalism of the information model of a neural network and a neuron and the streaming model of obtaining the results of calculations or measurements in a fuzzy computing environment at the level of network models and algorithms described above allows implementing such an architecture (structure) of an intelligent streaming computing and information-measuring system in which the result formation environment and information processes logically and functionally organized, based on the following principles. Firstly, computing - 1) the principle of interaction of objects (symbolic chains) of the computing environment with the information virtual environment; 2) the principle of virtual perspective in the design operator; 3) the principle of connectedness of the calculation results. Secondly, localities that determine the following important properties of the mechanism for obtaining results in various aspects, namely: 1) physical locality is due to limitations of a hardware-algorithmic nature; 2) temporal locality is due to quantization in physical time and algorithmic restrictions in information time; 3) the information locality or step of the information coordinate system is determined by the number of significant digits of the results obtained in the local range of values; 4) model locality is determined by the scope of the discrete linearized model for obtaining the results of calculations or measurements in the vicinity of nodes of the information coordinate system. The foregoing disclosure and description of the invention are an interpretation and explanation of the invention. Those skilled in the art to which this invention relates will understand that various modifications of the details and embodiments of the processes and structures described herein in order to explain the nature of the invention can be made without departing from the principles and / or essence of the invention.

Any equivalent formulation of the above-described entity-objects is within the scope of the present invention. Finally, any equivalent formulation of an intelligent streaming computing or information-measuring system under conditions of isolation, restriction, exchange, small scales, and uncertainty based on a streaming model of obtaining the result of calculations or measurements under the indicated conditions is within the scope of the present invention.

Accordingly, the scope of the invention should be determined by the attached claims and their legal equivalents.

Literature

1. Kalyaev I.A., I.I. Levin. Reconfigurable multi-conveyor computing systems for solving streaming problems. - Information Technologies and Computing Systems, 2011, No. 2, p. 12-22.

2. Myshev A.V. The information model of the neural network in the technologies of computational intelligence and forms of implementation of computing. - Information Technology. 2012, No. 1, p. 63-79.

3. Myshev A.V. A virtual streaming computing system based on an information model of an artificial neural network and neuron. Patent for invention No. 2530270. - The official bulletin "Inventions. Utility Models", 2014, No. 28, 30 pp.

4. Myshev A.V. The virtual perspective method in modeling "fuzzy" tasks. - Information Technologies and Computing Systems, 2011, No. 3, p. 66-79.

5. Myshev A.V. Metrological theory of the dynamics of interacting objects in the information field of a neural network. - Information Technology, 2012, No. 11, p. 52-62.

6. Myshev A.V. The model of active memory on binary fields in virtualization technologies for data transmission and storage channels. - Software products and systems, 2010, No. 1, p. 54-59.

7. Myshev A.V. Dynamics of information processes in computational technologies of computer modeling. / Proceedings of the ISA RAS, vol. 58. - M.: KRASAND, 2010, p. 137-148.

8. Myshev A.V. Computing and modeling the fuzzy Cauchy problem using the virtual perspective method - Software products and systems. 2012, No.3, p. 217-227.

Explanations for figures.

1. Fig. 1. Schematic representation of the information model of a neural network as a mathematical and logical prototype of the architecture of an intelligent virtual computing and information-measuring system.

2. Fig. 2. A geometric illustration of a multi-layer and multi-module scheme for implementing intelligent virtual computing and information-measuring systems.

3. Fig. 3. Schematic representation of the virtual memory model of an intelligent computing or information-measuring system in the form of a union of subsets of active and passive cells.

4. Fig. 4. A schematic drawing illustrating the operation of a design operator in a fuzzy computing environment.

Claims (1)

A method of constructing an intelligent streaming computing and information-measuring system with a fuzzy computing environment based on the information model of an artificial neural network and neuron and a streaming model for obtaining calculation and measurement results, characterized in that the logical organization of the architecture of an intelligent streaming computing and information-measuring system with a fuzzy environment calculations are implemented according to the principle of a multi-layer and multi-module system, which includes a processor layer, a layer of modules for preparing input data streams and / or measurement streams in the form of a logical data structure for the corresponding stream tasks, active virtual memory layers for each processor element (PE) and PE groups, general active virtual memory layers available for all PE, layers - processor , preparation of data streams and active virtual memory - have a modular partition, processor modules are logically and functionally implemented as a virtual streaming computing structure in accordance with the geometry and t the canopy of the information model of a neural network, the elements of which logically and informationally perform the functions of neurons, and the interaction between them is implemented according to the same principles as the neurons in the designated neural network model, the basic and forming elements of virtual memory modules of different layers are virtual cells of various types (active and passive ), the physical space of the fuzzy computing environment of the modules of the processor layer and the modules of the preparation layer of the input data streams and / or measurement streams is formed by cells a active memory, the modules of different layers of active virtual memory include coordinate systems for information binding and verification of the results of computational and information-measuring processes with a given number of significant characters (digits), ensuring their control, reliability and accuracy at specific spatio-temporal scales, based on fractal criteria and informational connectivity of limited and fuzzy values of the flow of results of calculations and / or measurements in its information field, and the virtual model is blurred second medium in the information field of the data stream.

Images