Neural Distributed Representations of Vector Data in Intelligent Information Technologies

Abstract

Introduction. Distributed representation (DR) of data is a form of a vector representation,where each object is represented by a set of vector components, and each vector component can belong to representations of many objects. In ordinary vector representations, the meaning of each component is defined, which cannot be said about DR. However, the similarity of RP vectors reflects the similarity of the objects they represent.DR is a neural network approach based on modeling the representation of information in the brain, resulted from ideas about a "distributed" or "holographic" representations. DRs have a large information capacity, allow the use of a rich arsenal of methods developed for vector data, scale well for processing large amounts of data, and have a number of other advantages. Methods for data transformation to DRs have been developed for data of various types -from scalar and vector to graphs.The purpose of the article is to provide an overview of a part of the work of the Department of Neural Information Processing Technologies (International Center) in the field of neural network distributed representations. The approach is a development of the ideas of Nikolai Mikhailovich Amosov and his scientific school of modeling the structure and functions of the brain.Scope. The formation of distributed representations from the original vector representations of objects using random projection is considered. With the help of the DR, it is possible to efficiently estimate the similarity of the original objects represented by numerical vectors. Gritsenko V.I., Rachkovskij D.A., Revunova E.G. ISSN 2519-2205 (Online), ISSN 0454-9910 (Print). Киб. и выч. техн. 2018. № 4 (194) 8The use of DR allows developing regularization methods for obtaining a stable solution of discrete ill-posed inverse problems, increasing the computational efficiency and accuracy of their solution, analyzing analytically the accuracy of the solution. Thus DRs allow for increasing the efficiency of information technologies applying them.Conclusions. DRs of various data types can be used to improve the efficiency and intelligence level of information technologies. DRs have been developed for both weakly structured data, such as vectors, and for complex structured representations of objects, such as sequences, graphs of knowledge-base situations (episodes), etc. Transformation of different types of data into the DR vector format allows unifying the basic information technologies of their processing and achieving good scalability with an increase in the amount of data processed.In future, distributed representations will naturally combine information on structure and semantics to create computationally efficient and qualitatively new information technologies in which the processing of relational structures from knowledge bases is performed by the similarity of their DRs. The neurobiological relevance of distributed representations opens up the possibility of creating intelligent information technologies based on them that function similarly to...

Neural Distributed Representations for Artificial Intelligence and Modeling of Thinking

“…The general APNN architecture. The APNN architecture was proposed and developed in [6,[14][15][16][17][18]. It is generally recognized that for a reasonable common-sense behavior, an intelligent agent needs a model of the world that includes knowledge specific to the subject area, as well as information about the agent itself.…”

“…Models should exist for objects of different nature, for example, events, objects, feelings, features, etc. Models (their representations) of different modalities can be combined, which leads to multimodal representations of objects and their associations with behavioral schemes (reactions to objects or situations), see [6,[14][15][16][17][18].…”

Neural Autoassociative Memories for Binary Vectors: A Survey

“…Note that such data representation schemes by similarity preserving binary vectors have been developed for objects represented by various data types, mainly for (feature) vectors (see survey in [131]), but also for structured data types such as sequences [102,72,85,86] and graphs [127,128,148,136,62,134]. A significant part of this research is developed in the framework of distributed representations [45,76,106,126,89], including binary sparse distributed representations [102,98,103,127,128,113,114,137,138,139,148,135,136,61,134,129,130,131,132,31,33] and dense distributed representations [75,76] (see [82,84,87,88,83] for examples of their applications).…”

Recovering Signals Obtained by Indirect Measurements Based on Truncated Singular Value Decomposition and Random Projection

“…Авторами [4][5][6][7] разрабатывается подход, основанный на поиске минимума ошибки решения дискретной некорректной за-дачи с использованием случайного проецирования, обеспечивающего устойчивость решения и позволяющего понизить вычислительную сложность. Случайное проецирование -разновидность методов формирования нейросетевых распределенных представлений [28][29][30][31][32][33].…”