Search

In this paper, we propose a Vector Semiotic Model as a possible solution to the symbol grounding problem in the context of Visual Question Answering. The Vector Semiotic Model combines the advantages of a Semiotic Approach implemented in the Sign-Based World Model and Vector Symbolic Architectures. The Sign-Based World Model represents information about a scene depicted on an input image in a structured way and grounds abstract objects in an agent’s sensory input. We use the Vector Symbolic Architecture to represent the elements of the Sign-Based World Model on a computational level. Properties of a high-dimensional space and operations defined for high-dimensional vectors allow encoding the whole scene into a high-dimensional vector with the preservation of the structure. That leads to the ability to apply explainable reasoning to answer an input question. We conducted experiments are on a CLEVR dataset and show results comparable to the state of the art. The proposed combination of approaches, first, leads to the possible solution of the symbol-grounding problem and, second, allows expanding current results to other intelligent tasks (collaborative robotics, embodied intellectual assistance, etc.).

Problem and purpose. Along with the obvious benefits, the digitalization of society carries its own risks. At the same time, in modern psychology there is not enough information about the differences in representations of such risks in different cultures. The purpose of the article is to empirically verify the assumption about the dependence of risk perceptions on the socio-cultural context. Methodology. The empirical part of the study was carried out through questionnaires, collected in different universities in three countries during academic and scientific visits (Russia: n = 112, Romania: n = 94, Brazil: n = 98) and drafting the evaluation reports of social risks perceptions (Abric coefficient). During the translation of the questionnaires, we used the focus group method and the method of translation of psychodiagnostic tools and questionnaires (S.V. Kudrya). Results. The data obtained showed that perceptions of risks depend on general perceptions of risks in the culture of a given country, legislation in the field of Internet security, as well as the duration and experience of interaction in social networks of the Internet. Thus, the" core " of the social representation of Russian and Romanian students about the results of risky behavior on the Internet are unproductive behavior in the information environment (TCP-92); demonstration of indifference (TCP-78) or aggressiveness (TCP-75), and for the Brazilian sample, the demonstration of psychological affliction is more typical (TCP-65). In addition, the lexical-semantic analysis of terms and concepts in the field of riskology used for empirical survey of students showed the presence of semantic cross-cultural differences in their understanding. Discussion and conclusion. The data obtained allow us to say that social perceptions of risks are influenced by socio-cultural and legislative peculiarities: the empirical part of the study showed a clear difference between the “core” and “periphery” both in the cross-cultural dimension and within the country samples. The lexico-semantic analysis of risk-generating behavioral patterns and ideas about risks showed cultural (linguistic) differences in this area and the need not only for adaptation and verification of diagnostic tools, but also for clarifying the meaning of various risk factors in the verbal plan.

Deep learning and especially deep reinforcement learning usually require huge amount of data for training and simulators using is perspective approach to provide this data. Model trained in simulator can be transferred on real robot without wasting a lot of time to collect data. Training in simulator also allows using of different techniques to speed up convergence and increase resulting performance. One of them is to train feature-based model with access to the whole information about the environment and use it as expert for main image-based model. This reduces earning time and the computational costs that are necessary to obtain quality results with image-based model. In this work we improve idea of behaviour cloning feature agent and make it more flexible with using of expert demonstrations forgetting. We conducted experiments on transfer learning for a robotic manipulator that interacts with complex objects and compared them with classic off-policy approaches.

The article is dedicated to the theoretical study of the process of convergence and integration of the digital and predigital environments. The general and distinctive features of the following concepts: “information society”, “information environment”, “digital environment” in terms of influence on an individual and on a social group are presented. Based on psychological research in various areas, the authors present a classification of stages where the convergence of the digital and pre-digital environment takes place. The concept of “interference” and its application in psychology and the related disciplines is revealed; the authors’ understanding of interference to describe the area of merging and integration of the digital and pre-digital environments is showcased. The results of the research can be of significance in the study of digital environments in both theoretical and empirical research, explaining the digital transformation of the subject.

Nowadays our knowledge of the brain is actively getting wider. Hierarchical Temporal Memory is the technology that arose due to new discoveries in neurobiology, such as research on the structure of the neocortex. One of the most popular applications of this technology is image recognition and anomaly detection. Nevertheless, both in the neocortex and in hierarchical temporal memory an image is recognized by its parts. Therefore, there is a problem of choosing the most meaningful parts of an image in order to perform fast and effective recognition. In this work we propose the architecture that unites Hierarchical Temporal Memory and Reinforcement Learning in order to find the optimal way of image exploration. Besides, we prove by experiments that this architecture is effective, and the quality of the resulting movement pattern is high.

In the last years, deep learning and reinforcement learning methods have significantly improved mobile robots in such fields as perception, navigation, and planning. But there are still gaps in applying these methods to real robots due to the low computational efficiency of recent neural network architectures and their poor adaptability to robotic experiments’ realities. In this article, we consider an important task in mobile robotics - navigation to an object using an RGB-D camera. We develop a new neural network framework for robot control that is fast and resistant to possible noise in sensors and actuators. We propose an original integration of semantic segmentation, mapping, localization, and reinforcement learning methods to improve the effectiveness of exploring the environment, finding the desired object, and quickly navigating to it. We created a new HISNav dataset based on the Habitat virtual environment, which allowed us to use simulation experiments to pre-train the model and then upload it to a real robot. Our architecture is adapted to work in a real-time environment and fully implements modern trends in this area.

OBJECTIVE The aim: To determine the morphometric parameters of the parenchymal and stromal liver components of healthy newborns. PATIENTS AND METHODS Material and methods: The morphometric investigation included 45 liver tissue biopsies of healthy newborns. All morphometric parameters of the parenchymal and stromal liver components were calculated using the Avtandilov microscopic morphometric grid. It was inserted into the microscope ocular tube with a total × 200 microscope magnification. The number of points that were found on the corresponding types of parenchymal and stromal liver components was calculated. In every case, it was selected 10 random microscopic areas and then all data were obtained, calculated and presented as percentages. RESULTS Results: Morphometric parameters of hepatocytes: mononuclear hepatocytes - 93.5±7.1 %, two-nuclear hepatocytes - 6.5±1.2 %, BMHC (bi-/mononuclear hepatocytes coefficient) - 0.06±0.01, hepatocytes with fat vacuoles - 0.5±0.2 %. Parenchymal and stromal liver components: parenchyma - 74.2±4.3 %, stroma (including blood vessels and bile ducts) - 25.8±2.6 %, SPI (stroma/parenchyma index) - 0.34±0.01. Morphometric parameters of all of the liver components: hepatocytes - 74.2±4.3 %, portal tracts - 3.1±0.6 %, central veins - 9.3±1.4 %, sinusoids - 10.5±1.3 %, bile ducts - 2.9±0.2 %. Expression level parameters: fibronectin - 17.3±2.5 %, collagen type I - 9.7±1.9 %, collagen type III - 10.1±0.9 %, collagen type IV - 5.9±0.2 %. Parameters of liver fibrosis biomarkers: APRI (index) - 0.19±0.01, а FIB-4 (index) - 0.022±0.001. CONCLUSION Conclusions: The morphometric parameters of the parenchymal and stromal liver components of healthy newborns can be used as a control group in the study of any pathological conditions of the liver of newborns.

This paper considers a sign-based approach to the problem of modeling the goal-setting process and integrating it with behavior planning methods. The GoalMAP algorithm, which is based on a psychologically plausible sign-based world model of a cognitive agent, is proposed. The algorithm implements an iterative hierarchical planning process with emphasis on the stage of setting or selecting a new goal. The complexity of the behavior planning algorithm is estimated. Model experiments with a software implementation of the constructed algorithms that demonstrates key features of the adopted approach are performed.

In the last few years, there is a growing interest in offline reinforcement learning (offline RL) and in reinforcement learning (RL) in general. In this paper, we presented an example of applying some of these methods to the debt collection process. We conducted several experiments using DQN, Munchausen DQN, DRQN and CQL modification for creating an optimal agent for our problem. As a result, we showed that CQL and Munchausen DQN could be successfully used in offline RL setting for debt collection process. Moreover, these agents show performance comparable with baseline DDQN agent but have several advantages for mentioned problem. We also described some practical obstacles in the usage of RL agents in a real-life task.

Among a number of problems in the behavior planning of an unmanned vehicle the central one is movement in difficult areas. In particular, such areas are intersections at which direct interaction with other road agents takes place. In our work, we offer a new approach to train of the intelligent agent that simulates the behavior of an unmanned vehicle, based on the integration of reinforcement learning and computer vision. Using full visual information about the road intersection obtained from aerial photographs, it is studied automatic detection the relative positions of all road agents with various architectures of deep neural networks (YOLOv3, Faster R-CNN, RetinaNet, Cascade R-CNN, Mask R-CNN, Cascade Mask R-CNN). The possibilities of estimation of the vehicle orientation angle based on a convolutional neural network are also investigated. Obtained additional features are used in the modern effective reinforcement learning methods of Soft Actor Critic and Rainbow, which allows to accelerate the convergence of its learning process. To demonstrate the operation of the developed system, an intersection simulator was developed, at which a number of model experiments were carried out.

In this paper, we propose a biologically plausible model for learning the decision-making sequence in an external environment with internal motivation. As a computational model, we propose a hierarchical architecture of an intelligent agent acquiring experience based on reinforcement learning. We use the basal ganglia model to aggregate a reward, and sparse distributed representation of states and actions in hierarchical temporal memory elements. The proposed architecture allows the agent to build a compact model of the environment and to form an effective strategy, which is experimentally demonstrated to search for resources in grid environments.

The textbook is intended for the development of theoretical material and the implementation of the course work of bachelors in the field of preparation 35.03.06 Agroengineering of the Federal State Educational Institution of Higher Education, the focus "Machinery and equipment for the storage and processing of agricultural products" contains information on the basic methods of calculating transport and technological equipment of processing enterprises of crop production. The textbook contains the information necessary for the formation of professional competencies in the preparation of bachelors in the direction of 35.03.06 "Agroengineering" and is recommended by the Scientific and Methodological Council on Technologies, Means of Mechanization and Energy Equipment in Agriculture of the Federal UMO for Agriculture, Forestry and Fisheries for use in the educational process.

This paper explores an application of image augmentation in reinforcement learning tasks - a popular regularization technique in the computer vision area. The analysis is based on the model-free off-policy algorithms. As a regularization, we consider the augmentation of the frames that are sampled from the replay buffer of the model. Evaluated augmentation techniques are random changes in image contrast, random shifting, random cutting, and others. Research is done using the environments of the Atari games: Breakout, Space Invaders, Berzerk, Wizard of Wor, Demon Attack. Using augmentations allowed us to obtain results confirming the significant acceleration of the model’s algorithm convergence. We also proposed an adaptive mechanism for selecting the type of augmentation depending on the type of task being performed by the agent.

Exploration is an essential part of reinforcement learning, which restricts the quality of learned policy. Hard-exploration environments are defined by huge state space and sparse rewards. In such conditions, an exhaustive exploration of the environment is often impossible, and the successful training of an agent requires a lot of interaction steps. In this paper, we propose an exploration method called Rollback-Explore (RbExplore), which utilizes the concept of the persistent Markov decision process, in which agents during training can roll back to visited states. We test our algorithm in the hard-exploration Prince of Persia game, without rewards and domain knowledge. At all used levels of the game, our agent outperforms or shows comparable results with state-of-the-art curiosity methods with knowledge-based intrinsic motivation: ICM and RND. An implementation of RbExplore can be found at https://github.com/cds-mipt/RbExplore.

In recent years, the task of visual question answering (VQA) at the intersection of computer vision and natural language processing is gaining interest in the scientific community. Even though modern systems achieve good results on standard datasets, these results are far from what is achieved in Computer Vision or Natural Language Processing separately, for example, in tasks of image classification or machine translation. One of the reasons for this phenomenon is the problem of modelling the interaction between modalities, which is partially solved by using the attention mechanism, as, for example, in the models used in this paper. Another reason lies in the statement of the problem itself. In addition to the problems inherited from CV and NLP, there are problems associated with the variety of situations shown in the picture and the possible questions for them. In this paper, we analyze errors for the state-of-the-art approaches and separate them into several classes: text recognition errors, answer structure, entity counting, type of the answer, and ambiguity of an answer. Text recognition errors occur when answering a question like “what is written in ..?” and associated with the representation of the image. Errors in the answer structure are associated with the reduction of the VQA to the classification task. Entity counting is a known weakness of current models. A typical situation of errors in the type of answer is when the model answers the “Yes/No” question in a different way. Errors from the ambiguity of an answer class occur when the model produces an answer that is correct in meaning but does not coincide with the formulation of the ground truth. Addressing these types of errors will lead to the overall improvement of VQA systems.

Indoor navigation is one of the main tasks in robotic systems. Most decisions in this area rely on ideal agent coordinates and a pre-known room map. However, the high accuracy of indoor localization cannot be achieved in realistic scenarios. For example, the GPS has low accuracy in the room; odometry often gives much noise for accurate positioning, etc. In this paper, we conducted a study of the navigation problem in the realistic Habitat simulator. We proposed a method based on the neural network approach and reinforcement learning that takes into account these factors. The most promising recent approaches were DDPPO and ANM for agent control and DF-VO for localization, during the analysis of which a new approach was developed. This method takes into account the non-determinism of the robot’s actions and the noise level of data from its sensors.

OBJECTIVE: The objective of the study was to determine the specifics of the stromal and parenchymal liver components of 0–6-month-old children from HIV-monoinfected mothers. METHODS: The morphometric investigation included 84 liver tissue biopsies of 0–6-month-old dead children from HIV-monoinfected mothers. All morphometric parameters of the parenchymal and stromal liver components were calculated using the Avtandilov’s microscopic morphometric grid, which was consisted of 100 equidistant points. It was inserted into the microscope’s ocular tube with a total ×200 microscope magnification. The number of points that were found on the corresponding types of parenchymal and stromal liver components was calculated. In every case, it was selected 10 random microscopic areas and then all data were obtained, calculated, and presented as percentages. RESULTS: Morphometric parameters of hepatocytes: Mononuclear hepatocytes – 87.3 ± 6.2% (control – 93.5 ± 7.1), two-nuclear hepatocytes – 12.7 ± 1.3% (control – 6.5 ± 1.2), two-/mononuclear hepatocytes coefficient – 0.14 ± 0.01 (control – 0.06 ± 0.01), and hepatocytes with fat vacuoles – 15.6 ± 1.8% (control – 0.5 ± 0.2). Parenchymal and stromal liver components: Parenchyma – 64.3 ± 2.1% (control – 74.2 ± 1.3), stroma (including blood vessels and bile ducts) – 35.7 ± 1.9% (control – 25.8 ± 1.6), and stroma/parenchyma index – 0.55 ± 0.01 (control – 0.34 ± 0.01). Morphometric parameters of all of the liver components: Hepatocytes – 64.3 ± 3.1% (control – 74.2 ± 4.3), portal tracts – 14.9 ± 1.9% (control – 3.1 ± 0.6), central veins – 9.3 ± 1.3 % (control – 9.3 ± 1.4), sinusoids – 8.8 ± 1.1% (control – 10.5 ± 1.3), and bile ducts – 2.7 ± 0.2% (control – 2.9 ± 0.2). Expression level parameters: Fibronectin – 64.8 ± 4.1% (control – 17.3 ± 2.5), collagen Type I – 13.6 ± 1.7% (control – 9.7 ± 1.9), collagen Type III – 15.3 ± 1.4% (control – 10.1 ± 0.9), and collagen Type IV – 6.8 ± 0.2% (control – 5.9 ± 0.2). CONCLUSIONS: It was established that in the liver of 0–6-month-old dead children from HIV-monoinfected mothers, the parenchymal component of the liver showed the signs of its reduction, increase of regenerative activity of hepatocytes, and fatty degeneration of hepatocytes with a certain sign of reactive steatohepatitis. Furthermore, it was established that the stromal component of the liver of children from HIV-infected mothers showed the signs of its progressive proliferation and collagenization due to increased production and accumulation of fibronectin, Type I, Type III collagens in the stroma of portal tracts and newly formed septa, and the signs of hepatic sinusoid capillarization due to Type IV collagen accumulation in the space of Disse of the hepatic sinusoids.

Today planning algorithms are among the most sought after. One of the main such algorithms is Monte Carlo Tree Search. However, this architecture is complex in terms of parallelization and development. We presented possible approximations for the MCTS algorithm, which allowed us to significantly increase the learning speed of the agent.

This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning. One of the mechanisms that are used to solve this problem in the area of reinforcement learning is a model-based approach. In the paper we are expanding the schema networks method which allows to extract the logical relationships between objects and actions from the environment data. We present algorithms for training a Delta Schema Network (DSN), predicting future states of the environment and planning actions that will lead to positive reward. DSN shows strong performance of transfer learning on the classic Atari game environment.

In the paper, we consider the problem of the robotic movement inaccuracy. We suggest that clarifying the abstract actions of the behavior planner will help build more precise control of the robot. A multi-agent planner for the synthesis of the abstract actions with refinement for a two-dimensional movement task was proposed. We analyze the problem of the action execution by robots and present a way to solve navigation problems through the use of reinforcement learning and deep learning algorithms. This method made it possible to synthesize sets of atomic sub-actions for correcting the state of the robotic platform at each moment of time. We conducted a set of experiments in single and multiagent settings. The synthesis of sub-actions of several tasks formed a training set for the RL model, which was tested on a test example. All considered tasks consisted of moving robotic platforms across a map with obstacles and manipulating environmental objects.

Single-shot grid-based path finding is an important problem with the applications in robotics, video games etc. Typically in AI community heuristic search methods (based on A* and its variations) are used to solve it. In this work we present the results of preliminary studies on how neural networks can be utilized to path planning on square grids, e.g. how well they can cope with path finding tasks by themselves within the well-known reinforcement problem statement. Conducted experiments show that the agent using neural Q-learning algorithm robustly learns to achieve the goal on small maps and demonstrate promising results on the maps have ben never seen by him before.

We carried out an empirical study of aggression in relation to different personal traits. In this article we present results obtained for different forms of aggression, including results of machine-learning experiments with the AQJSM method. The method distinguishes several classes with different levels of aggression defined with a special form, as well as making causal inferences with AQ preprocessing and the first stage of JSM method of extraction of cause and effect relationships. The proposed method produces acceptable results for both small datasets and big data with incomplete information.

Subwavelength optical resonators and scatterers are dramatically expanding the toolset of the optical sciences and photonics engineering. By offering the opportunity to control and shape light waves in nanoscale volumes, recent developments using high-refractive-index dielectric scatterers gave rise to efficient flat-optical components such as lenses, polarizers, phase plates, color routers, and nonlinear elements with a subwavelength thickness. In this work, we take a deeper look into the unique interaction of light with rod-shaped amorphous silicon scatterers by tapping into their resonant modes with a localized subwavelength light source-an aperture scanning near-field probe. Our experimental configuration essentially constitutes a dielectric antenna that is locally driven by the aperture probe. We show how leaky transverse electric and magnetic modes can selectively be excited and form specific near-field distribution depending on wavelength and antenna dimensions. The probe's transmittance is furthermore enhanced upon coupling to the Fabry-Perot cavity modes, revealing all-dielectric nanorods as efficient transmitter antennas for the radiation of subwavelength emitters, in addition to constituting an elementary building block for all-dielectric metasurfaces and flat optics.

Behavior planning is an important function of any complex technical facility intelligent control system. Presently, a symbol paradigm of artificial intelligence offers a variety of planning algorithms, including those that use precedent information, i.e. algorithms based on acquired knowledge. A symbol grounding problem within the exiting approaches of knowledge representation does not allow effective use the developed algorithms together with learning mechanisms for the purpose of solving a wide variety of applied problems by actual intelligent agents (robotics systems). This article presents the original planning algorithm (MAP Planner), which uses a sign world model as the basis for acquisition and maintenance of knowledge for future use in behavior planning. the sign problem approach describes planning as a cognitive function actualized by the world model of a subject of activity. Apart from solving symbol grounding problems and ensuring psychological and biological plausibility, a sign planning process model allows interaction of an intelligent agent with other participants in solving a cooperative task. The article presents the description of the knowledge representation method used, a MAP planning algorithm, and a model experiment in a “block world”.

Hierarchies are used in reinforcement learning to increase learning speed in sparse reward tasks. In this kind of tasks, the main problem is elapsed time, required for the initial policy to reach the goal during the first steps. Hierarchies can split a problem into a set of subproblems that could be reached in less time. In order to implement this idea, Hierarchical Reinforcement Learning (HRL) algorithms need to be able to learn the multiple levels within a hierarchy in parallel, so these smaller subproblems could be solved at the same time. Most famous existing HRL algorithms that can learn multi-level hierarchies are not able to efficiently learn levels of policies simultaneously, especially in continuous space and action space environment. To address this problem, we had analyzed the newest existing framework, Hierarchical Actor-Critic with Hindsight (HAC), test it in the simulated mobile robot environment and determine the optimal configuration of parameters and ways to encode information about the environment states.

Hierarchical reinforcement learning (HRL) is another step towards the convergence of learning and planning methods. The resulting reusable abstract plans facilitate both the applicability of transfer learning and increasing of resilience in difficult environments with delayed rewards. However, on the way of the practical application of HRL, especially in robotics, there are a number of difficulties, among which the key is a semi-manual task of the creation of the hierarchy of actions, which the agent uses as a pre-trained scheme. In this paper, we present a new approach for simultaneous constructing and applying the hierarchy of actions and sub-goals. In contrast to prior efforts in this direction, the method is based on a united loop of clustering of the environment’s states observed by the agent and allocation of sub-targets by the modified bottleneck method for constructing of abstract machines hierarchy. The general machine is built using the so-called programmable schemes, which are quite universal for the organization of transfer learning for a wide class of tasks. A particular abstract machine is assigned for each set of clustered states. The goal of each machine is to reach one of the found bottleneck states and then get into another cluster. We evaluate our approach using a standard suite of experiments on a challenging planning problem domain and show that our approach facilitates learning without prior knowledge.

The article expounds the functional of a cognitive architecture Sign-Based World Model (SBWM) through the algorithm for the implementation of a particular case of reasoning. The SBWM architecture is a multigraph, called a semiotic network with special rules of activation spreading. In a semiotic network, there are four subgraphs that have specific properties and are composed of constituents of the main SBWM element – the sign. Such subgraphs are called causal networks on images, significances, personal meanings, and names. The semiotic network can be viewed as the memory of an intelligent agent. It is proposed to divide the agent’s memory in the SBWM architecture into a long-term memory consisting of signs-prototype, and a working memory consisting of signs-instance. The concept of elementary mental actions is introduced as an integral part of the reasoning process. Examples of such actions are provided. The performance of the proposed reasoning algorithm is considered by a model example.

Standard robotic control works perfectly in case of ordinary conditions, but in the case of a change in the conditions (e.g. damaging of one of the motors), the robot won’t achieve its task anymore. We need an algorithm that provide the robot with the ability of adaption to unforeseen situations. Reinforcement learning provide a framework corresponds with that requirements, but it needs big data sets to learn robotic tasks, which is impractical. We discuss using Gaussian processes to improve the efficiency of the Reinforcement learning, where a Gaussian Process will learn a state transition model using data from the robot (interaction) phase, and after that use the learned GP model to simulate trajectories and optimize the robot’s controller in a (simulation) phase. PILCO algorithm considered as the most data efficient RL algorithm. It gives promising results in Cart-pole task, where a working controller was learned after seconds of (interaction) on the real robot, but the whole training time, considering the training in the (simulation) was longer. In this work, we will try to leverage the abilities of the computational graphs to produce a ROS friendly python implementation of PILCO, and discuss a case study of a real world robotic task.

The “curse of dimensionality” and environments with sparse delayed rewards are one of the main challenges in reinforcement learning (RL). To tackle these problems we can use hierarchical reinforcement learning (HRL) that provides abstraction both on actions and states of the environment. This work proposes an algorithm that combines hierarchical approach for RL and the ability of neural networks to serve as universal function approximators. To perform the hierarchy of actions the options framework is used which main idea is to utilize macro-actions (the sequence of simpler actions). State of the environment is the input to a convolutional neural network that plays a role of Q-function estimating the utility of every possible action and skill in the given state. We learn each option separately using different neural networks and then combine result into one architecture with top-level approximator. We compare the performance of the proposed algorithm with the deep Q-network algorithm (DQN) in the environment where the aim of the magnet-arm robot is to build a tower from bricks.

The modern trend of education development is digitalization, transition from conventional classroom offline model to distance online education. Formation of global digital society was accelerated due to the COVID–19 pandemic, when significant portion of Earth population, including students, was forced to work, to study distantly. In this regard, this article discusses the responses of Russian system of higher education to current challenges of digitalization. This article analyzes interactive educational technologies of online, digital, e-learning, visualization and gamification of education, implementation of network structures. On the basis of analysis of the modern state of Russian higher education, the unsolved key issues are demonstrated as well as the main trends of the required changes. This work describes the urgent issues of development of regulatory framework of digital education, intensification of development of digital infrastructure of universities, digital training and further training of teachers and students, analysis and actualization of existing specialties and fields. Solution of the mentioned issues requires for legislative, organizational, administrative, technological, teaching and learning efforts of the country, universities, and society. A response of the Russian system of higher education to the challenges of digitalization can be comprised of formation of unified information and education portal of national universities, designing a model of digital university.

This paper describes the application of hierarchical temporal memory (HTM) to the task of anomaly detection in human motions. A number of model experiments with well-known motion dataset of Carnegie Mellon University have been carried out. An extended version of HTM is proposed, in which feedback on the movement of the sensor’s focus on the video frame is added, as well as intermediate processing of the signal transmitted from the lower layers of the hierarchy to the upper ones. By using elements of reinforcement learning and feedback on focus movement, the HTM’s temporal pooler includes information about the next position of focus, simulating the human saccadic movements. Processing the output of the temporal memory stabilizes the recognition process in large hierarchies.

The paper discusses the interaction between methods of modeling reasoning and behavior planning in a sign-based world model for the task of synthesizing a hierarchical plan of relocation. Such interaction is represented by the formalism of intelligent rule-based dynamic systems in the form of alternate use of transition functions (planning) and closure functions (reasoning). Particular attention is paid to the ways of information representation of the object spatial relationships on the local map and the methods of organizing pseudo-physical reasoning in a sign-based world model. The paper presents a number of model experiments on the relocation of a cognitive agent in different environments and replenishment of the state description by means of the variants of logical inference.

Procedures for forming an element of an actor's world model (sign) introduced in the first part of this study are considered. The process of forming the pair image---sign significance taking into account the modern understanding of the human brain cortex operation is investigated. An algorithm for synthesizing a behavior plan is constructed, and a novel architecture of intelligent agents that are able, among other things, to distribute roles in coalitions is proposed.

At the moment reinforcement learning have advanced significantly with discovering new techniques and instruments for training. This paper is devoted to the application convolutional and recurrent neural networks in the task of planning with reinforcement learning problem. The aim of the work is to check whether the neural networks are fit for this problem. During the experiments in a block environment the task was to move blocks to obtain the final arrangement which was the target. Significant part of the problem is connected with the determining on the reward function and how the results are depending in reward’s calculation. The current results show that without modifying the initial problem into more straightforward ones neural networks didn’t demonstrate stable learning process. In the paper a modified reward function with sub-targets and euclidian reward calculation was used for more precise reward determination. Results have shown that none of the tested architectures were not able to achieve goal.

We present a model of Reinforcement Learning, which consists of modified neural-network architecture with spatio-temporal connections, known as Temporal Hebbian Self-Organizing Map (THSOM). A number of experiments were conducted to test the model on the maze solving problem. The algorithm demonstrates sustainable learning, building a near to optimal routes. This work describes an agents behavior in the mazes of different complexity and also influence of models parameters at the length of formed paths.

The paper considers the task of the group’s collective plan intellectual agents. Robotic systems are considered as agents, possessing a manipulator and acting with objects in a determined external environment. The MultiMAP planning algorithm proposed in the article is hierarchical. It is iterative and based on the original sign representation of knowledge about objects and processes, agents knowledge about themselfs and about other members of the group. For distribution actions between agents in general plan signs “I” and “Other” (“They”) are used. In conclusion, the results of experiments in the model problem “Blocksworld” for a group of several agents are presented.

Functions that are referred in psychology as functions of consciousness are considered. These functions include reflection, consciousness of activity motivation, goal setting, synthesis of goal oriented behavior, and some others. The description is based on the concept of sign, which is widely used in psychology and, in particular, in the cultural-historical theory by Vygotsky, in which sign is interpreted informally. In this paper, we elaborate upon the concept of sign, consider mechanisms of sign formation, and some self-organization on the set of signs. Due to the work of self-organization mechanisms, a new method for the representation of the world model of an actor appears. The concept of semiotic network is introduced that is used for the examination of the actor's world models. Models of some functions indicated above are constructed. The second part of the paper is devoted to functions of self-consciousness and to the application of the constructed models for designing plans and constructing new architectures of intelligent agents that are able, in particular, to distribute roles in coalitions.

The feasibility of using a diffraction grating manufactured by laser photoinduced etching of the (001) surface of single-crystal InP and monatomic steps on a highly-oriented (0001) surface of pyrolytic graphite as reference samples for calibration of scanning near-field microscopes operating in the shear-force (quasifriction) mode is demonstrated.

Behavior planning is known to be one of the basic cognitive functions, which is essential for any cognitive architecture of any control system used in robotics. At the same time most of the widespread planning algorithms employed in those systems are developed using only approaches and models of Artificial Intelligence and don't take into account numerous results of cognitive experiments. As a result, there is a strong need for novel methods of behavior planning suitable for modern cognitive architectures aimed at robot control. One such method is presented in this work and is studied within a special class of navigation task called smart relocation task. The method is based on the hierarchical two-level model of abstraction and knowledge representation, e.g. symbolic and subsymbolic. On the symbolic level sign world model is used for knowledge representation and hierarchical planning algorithm, PMA, is utilized for planning. On the subsymbolic level the task of path planning is considered and solved as a graph search problem. Interaction between both planners is examined and inter-level interfaces and feedback loops are described. Preliminary experimental results are presented., As submitted to the 7th International Conference on Biologically Inspired Cognitive Architectures (BICA 2016), New-York, USA, July 16-19 2016

The feasibility of using a reconstructed 7×7-Si(111) surface and monatomic steps on this surface as reference samples for calibration of ultrahigh vacuum scanning tunneling microscopes is demonstrated.

Information relative to participation of the B. E. Vedeneev All-Russian Scientific-Research Institute of Hydraulic Engineering (VNIIG im. B. E. Vedeneeva) in the solution of problems of scientific verification of the design, construction, and operation of water-development works in regions of the Extreme North are presented. Basic characteristics of changes in the technical condition of high rock-and-earthfill dams, and the conditions under which their safety is ensured for long-term service in these regions are examined.

Criteria and principles of optimizing snow deposition in a system of runoff-regulating forest belts with respect to their direction relative to cardinal points, width of the space between belts, floristic and species composition, aerodynamic design, number of rows, and other indices.

Fianite is a promising multipurpose material for new electronic technologies owing to its unique combination of physical and chemical properties. It can be used in virtually all of the main technological stages of the production of micro-, opto-, and SHF-electronics; in particular, as a bulk dielectric substrate and a material for buffer layers in heteroepitaxy; as a material for insulating, antireflection, and protective layers in device elements; and as a gate dielectric [1–3]. In this work, we consider the possibilities for using fianite and ZrO2 as an antireflection coating for silicon solar cells (SCs) and SCs based on InGaAsP heterostructures.

Local polarization properties of a gold subwavelength grating with plasmon-induced linear dichroism are studied by scanning near-field optical dynamic polarimetry. Periodic modulation of linear dichroism with the period corresponding to the period of the grating and the contrast of 0.3 is found at the distance of λ/20 from the sample.

A prototype of a bolometer with a deep thermal feedback (TF) is described. It allows stabilization of the temperature of an absorbing film at a level of 700–800°C by the control of its thermal radiation. The prototype was tested on a light-ion accelerator and a T-11M tokamak. The results obtained confirm the possibility of practically realize such advantages of the TF bolometer over conventional devices as a fast response, direct measurement of the incident power, improved stability, and a reduced influence of the drift of the intrinsic parameters of the sensor. The questions of the selection of optimal structural parameters of such bolometers and calculation of their threshold characteristics are considered.