Alexander Vladimirovich Demidovskij

National Research University Higher School of Economics | HSE · Faculty of Information Technology and Computer Engineering

Due to industrial demands to handle increasing amounts of training data, lower the cost of computing one model at a time, and lessen the ecological effects of intensive computing resource consumption, the job of speeding the training of deep neural networks becomes exceedingly challenging. Adaptive Online Importance Sampling and IDS are two brand-n...

Widespread use of highly accurate and trustworthy deep learning architectures is becoming a noticeable trend in the industry. Model accuracy and inferencing performance traditionally remain the two important factors to be considered before model deployment to any business application. Additionally to these two requirements, the problem of model exp...

Construction of integrated neural-symbolic systems is an actual and challenging task. Such hybrid systems combine advantages of connectionist and symbolic approaches. In particular, neural-symbolic systems are characterized by robust learning and distributed neural computations. At the same time, they can be interpreted, described and analyzed in l...

Introduction: The construction of integrated neurosymbolic systems is an urgent and challenging task. Building neurosymbolic decision support systems requires new approaches to represent knowledge about a problem situation and to express symbolic reasoning at the subsymbolic level. Purpose: Development of neural network architectures and methods fo...

The current problem of developing new kinds of decision support systems for different categories of management personnel is addressed in this study. A critical feature of such systems is their distributed and decentralized nature, which enables the construction of next-generation information systems in the form of Multi-Agent Systems, Internet of T...

Modern neural network methods make it possible to obtain qualitative results that open the colossal potential for integrating them into industrial applications. Therefore, there is a need for systems like the OpenVINO Deep Learning Workbench to analyze and optimize neural networks’ performance on target devices. As the primary tool for inference, t...

The very first step towards a challenging goal of creation of monolithic generic neuro-symbolic systems is application of sub-symbolic ideas to particular symbolic algorithms like aggregation of fuzzy linguistic assessments during Linguistic Decision Making. A novel theoretical idea is to express this aggregation as structural manipulations and tra...

Among the problems of neural network design the challenge of explicit representing conditional structural manipulations on a sub-symbolic level plays a critical role. In response to that challenge the article proposes a computationally adequate method for design of a neural network capable of performing an important group of symbolic operations on...

Tensor Product Variable Binding is an important aspect of building the bridge between the connectionist approach and the symbolic paradigm. It can be used to represent recursive structures in the tensor form that is an acceptable form for neural networks that are highly distributed in nature and, therefore, promise computational benefits from using...

Building a bridge between symbolic and connectionist level of computations requires constructing a full pipeline that accepts symbolic structures as an input, translates them to distributed representation, performs manipulations with this representation equivalent to symbolic manipulations and translates it back to the symbolic structure. This work...

Popularity of social networks makes them an attractive field for analysis of users’ behavior, for example, based on the intention analysis of their posts and comments. In the linguistic theory only 25 types of intentions exist and can be joined in 5 supergroups. We use the dataset that contains directed oriented graphs which nodes store information...

In this paper we observe the opportunity to offer new methods of solving NP-hard problems which frequently arise in the domain of information management, including design of database structures and big data processing. In our research we are focusing on the Maximum Clique Problem (MCP) and propose a new approach to solving that problem. The approac...