Dmitri A. Rachkovskij

Learn More
Distributed representations were often criticized as inappropriate for encoding of data with a complex structure. However Plate's Holographic Reduced Representations and Kanerva's Binary Spatter Codes are recent schemes that allow on-the-fly encoding of nested compositional structures by real-valued or dense binary vectors of fixed dimensionality. In this(More)
The purpose of the paper is to design and test neural network structures and mechanisms for making use of the information that is contained in the character strings for more correct recognition of the characters constituting these strings. Two neural networks are considered in the paper; both networks are combined into a joint recognition system. The first(More)
We present an approach to similarity-based retrieval from knowledge bases that takes into account both the structure and semantics of knowledge base fragments. Those fragments, or analogues, are represented as sparse binary vectors that allow a computationally efficient estimation of structural and semantic similarity by the vector dot product. We present(More)
Dataset generators are useful for the evaluation of an algorithm’s performance because they allow control of the characteristics and amount of data used for benchmarking. We propose a dataset generator called DataGen that allows varying the number of input features and output classes, the complexity and realizations of class regions, the distributions of(More)
The paper develops a set of ideas and techniques supporting analogical reasoning throughout the life-cycle of terrorist acts. Implementation of these ideas and techniques can enhance the intellectual level of computer-based systems for a wide range of personnel dealing with various aspects of the problem of terrorism and its effects. The method combines(More)
We discuss several approaches to similarity preserving coding of symbol sequences and possible connections of their distributed versions to metric embeddings. Interpreting sequence representation methods with embeddings can help develop an approach to their analysis and may lead to discovering useful properties.