Alexey N . Averkin | REA Plekhanov (original) (raw)
Related Authors
Technological University Dublin, Ireland
Masdar Institute of Science and Technology
Uploads
Papers by Alexey N . Averkin
Describes the DARPA Explanatory Artificial Intelligence (XAI) program, which seeks to create arti... more Describes the DARPA Explanatory Artificial Intelligence (XAI) program, which seeks to create artificial intelligence systems whose learning models and solutions can be understood and properly validated by end users. DARPA considers XAI as artificial intelligence systems AI that can explain their decision to a human user, characterize their strengths and weaknesses, and how they will behave in the future. To achieve this goal, methods have been developed for constructing explainable models of intelligent systems that are effective explanatory interfaces and psychological models of users for effective explanation. The XAI development teams are described that solve these three problems by creating and developing explainable machine learning (ML) technologies, developing principles, strategies, and methods of human-computer interaction for obtaining effective explanations and applying psychological explanatory theories to assess the quality of XAI systems.
Pattern recognition and image analysis, Dec 1, 2023
Journal of physics, Dec 1, 2020
The main problem solved in this project is the analysis of big data using a system of computer pr... more The main problem solved in this project is the analysis of big data using a system of computer processing and recognition of satellite images, based on a deep neural network architecture. The goal of the project is to develop methodological, theoretical and practical aspects of building such systems in poorly formalized subject areas, as well as to study the possibilities and advantages of building predictive models for analyzing fresh water reserves and predicting the direction, speed and nature of the spread of large fires using such systems. and assessments of the economic impact of these natural disasters.
Научные труды Вольного экономического общества России, 2014
физико-математических наук, доцент, доцент кафедры информатики Российского экономического универс... more физико-математических наук, доцент, доцент кафедры информатики Российского экономического университета имени Г.В. Плеханова
Studies in fuzziness and soft computing, 2023
Научные труды Вольного экономического общества России, 2014
European Society for Fuzzy Logic and Technology Conference, 2007
Multiattribute evaluation of alternatives for the disposition of surplus weapons-usable plutonium... more Multiattribute evaluation of alternatives for the disposition of surplus weapons-usable plutonium on the base of fuzzy sets has been made.
Advances in intelligent systems and computing, 2023
Программные продукты и системы, Aug 27, 2014
Journal of physics, Dec 1, 2020
This article attempts to give an overview of several algorithms for extracting rules from an arti... more This article attempts to give an overview of several algorithms for extracting rules from an artificial neural network. The goal of this article is to find critical links three important parts of artificial intelligence – production models, fuzzy logic and deep learning. Such an approach will stimulate researchers in the field of soft computing to develop applied systems in the field of explanational artificial intelligence and machine learning.
Procedia Computer Science, 2017
Peer-review under responsibility of the scientific committee of the 9th International Conference ... more Peer-review under responsibility of the scientific committee of the 9th International Conference on Theory and application of Soft Computing, Computing with Words and Perception.
Describes the DARPA Explanatory Artificial Intelligence (XAI) program, which seeks to create arti... more Describes the DARPA Explanatory Artificial Intelligence (XAI) program, which seeks to create artificial intelligence systems whose learning models and solutions can be understood and properly validated by end users. DARPA considers XAI as artificial intelligence systems AI that can explain their decision to a human user, characterize their strengths and weaknesses, and how they will behave in the future. To achieve this goal, methods have been developed for constructing explainable models of intelligent systems that are effective explanatory interfaces and psychological models of users for effective explanation. The XAI development teams are described that solve these three problems by creating and developing explainable machine learning (ML) technologies, developing principles, strategies, and methods of human-computer interaction for obtaining effective explanations and applying psychological explanatory theories to assess the quality of XAI systems.
Pattern recognition and image analysis, Dec 1, 2023
Journal of physics, Dec 1, 2020
The main problem solved in this project is the analysis of big data using a system of computer pr... more The main problem solved in this project is the analysis of big data using a system of computer processing and recognition of satellite images, based on a deep neural network architecture. The goal of the project is to develop methodological, theoretical and practical aspects of building such systems in poorly formalized subject areas, as well as to study the possibilities and advantages of building predictive models for analyzing fresh water reserves and predicting the direction, speed and nature of the spread of large fires using such systems. and assessments of the economic impact of these natural disasters.
Научные труды Вольного экономического общества России, 2014
физико-математических наук, доцент, доцент кафедры информатики Российского экономического универс... more физико-математических наук, доцент, доцент кафедры информатики Российского экономического университета имени Г.В. Плеханова
Studies in fuzziness and soft computing, 2023
Научные труды Вольного экономического общества России, 2014
European Society for Fuzzy Logic and Technology Conference, 2007
Multiattribute evaluation of alternatives for the disposition of surplus weapons-usable plutonium... more Multiattribute evaluation of alternatives for the disposition of surplus weapons-usable plutonium on the base of fuzzy sets has been made.
Advances in intelligent systems and computing, 2023
Программные продукты и системы, Aug 27, 2014
Journal of physics, Dec 1, 2020
This article attempts to give an overview of several algorithms for extracting rules from an arti... more This article attempts to give an overview of several algorithms for extracting rules from an artificial neural network. The goal of this article is to find critical links three important parts of artificial intelligence – production models, fuzzy logic and deep learning. Such an approach will stimulate researchers in the field of soft computing to develop applied systems in the field of explanational artificial intelligence and machine learning.
Procedia Computer Science, 2017
Peer-review under responsibility of the scientific committee of the 9th International Conference ... more Peer-review under responsibility of the scientific committee of the 9th International Conference on Theory and application of Soft Computing, Computing with Words and Perception.