International and Social Impacts of Artificial Intelligence Technologies
The Working Paper focuses on possible impacts of related technologies, such as machine learning and autonomous vehicles, on international relations and society. The authors also examine the ethical and legal aspects of the use of AI technologies. The present Working Paper of the Russian International Affairs Council (RIAC) includes analytical materials prepared by experts in the field of artificial intelligence, machine learning and autonomous system, as well as by lawyers and sociologists. The materials presented here are intended to contribute to the public dialogue on issues of artificial intelligence and the possible consequences of using this technology.
The 18 full and 13 short papers presented were carefully reviewed and selected from 255 submissions. There were organized in topical sections named: Image Processing, Pattern Analysis and Machine Vision; Information and Data Convergence; Disruptive Technologies for Future; E-Governance and Smart World
The 2018 Global Smart Industry Conference is organized in order to exchange experience, promote discussion and presentation of research papers, and summarize results in development of innovative models, methods and technologies for the digital industry in universities, scientific and industrial associations of the Russian Federation as well as in foreign companies, and the experience of their implementation in large transnational and domestic industrial companies.
It will be held in Chelyabinsk, Russian Federation, on November 13-15, 2018.
The aim of the conference is to determine the prospects for the development of Smart Industry technologies, integration of industrial companies, scientific organizations and authorities to create promising technologies for the digital transformation of the industry.
Conference topics:Condition monitoring and control for intelligent manufacturing Industrial robotics Components of and sensors Wireless sensor and actuator networks Digital Twins technologies Additive manufacturing technologies Big data, machine learning and artificial intelligence for Industry 4.0 management Human-machine interaction in industrial systems Security and privacy protection in industrial networks Virtual and augmented realities for Industry 4.0 Cloud and high-performance computing for smart factory Basic research for Industry 4.0 New educational technologies for Industry 4.0
The article is based on the annual Perm All-Russian scientific and practical conference "Artificial intelligence in solving urgent social and economic problems of the XXI century" (http://www.permai.ru/files/26.05.2018.pdf). It is also a brief overview of the results of the Perm branch of the Scientific Council of the Russian Academy of Sciences on the methodology of artificial intelli- gence, as well as several departments of the Perm state University, Perm state humanitarian pedagogi- cal University, National research University Higher school of Economics, Perm state medical University. The review covers the works that develop and apply the methods of artificial intelligence in the classical sense, i.e., those methods that simulate human intellectual activity by simulating natural mechanisms.
These are expert systems, genetic algorithms, neural networks, fuzzy mathematics. The scientific priori- ty of Perm scientists in the development of theoretical foundations and practical applications of artificial intelligence is emphasized.
Keywords: Artificial intelligence, neural network, expert system, genetic algorithm, theory, prac- tice, modeling, forecasting, optimization, recognition, data processing, knowledge extraction.
The paper focues on the anthropocentric illusion that is common to modern discussions on artificial intelligence. The author concludes that the reality of technological development provokes the emergence of a radically new kind of intelligence, incomparable with human, and also inaccessible to the cognitive capabilities of human species. Marvin Minsky's theory of artificial intelligence is used as the base optics for such an analysis. The result of its application is a cluster of inhuman epistemologies discovered in the framework of the so-called nonhuman turn.
EWDTS-2019 explores the novel trends in testing, diagnosis, repair of microelectronic systems, and also cyber security, automotive, IoT, artificial intelligence.
Results of a research of a legal regime of the intellectual property items created by spontaneous programs (artificial intelligence or robots) are presented in article. The author reasons a conclusion according to which it is necessary to recognize the results received by artificial intelligence as the protected intellectual property items on which there is no copyright; each such object has to have automatically assigned identification number allowing to determine, first, by what artificial intelligence he is created to establish, secondly, the developer of the spontaneous program having the exclusive right not only to this program, but also to the object created by it.
The text highlights the role of logic gates in the distributed architecture of neural networks, in which a generalized control loop affects each node of computation to perform pattern recognition. In this distributed and adaptive architecture of logic gates, rather than applying logic to information top-down, information turns into logic, that is, a representation of the world becomes a new function in the same world description.
We extend the existing framework of semi-implicit variational inference (SIVI) and introduce doubly semi-implicit variational inference (DSIVI), a way to perform variational inference and learning when both the approximate posterior and the prior distribution are semi-implicit. In other words, DSIVI performs inference in models where the prior and the posterior can be expressed as an intractable infinite mixture of some analytic density with a highly flexible implicit mixing distribution. We provide a sandwich bound on the evidence lower bound (ELBO) objective that can be made arbitrarily tight. Unlike discriminator-based and kernel-based approaches to implicit variational inference, DSIVI optimizes a proper lower bound on ELBO that is asymptotically exact. We evaluate DSIVI on a set of problems that benefit from implicit priors. In particular, we show that DSIVI gives rise to a simple modification of VampPrior, the current state-of-the-art prior for variational autoencoders, which improves its performance.
We address the external effects on public sector efficiency measures acquired using Data Envelopment Analysis. We use the health care system in Russian regions in 2011 to evaluate modern approaches to accounting for external effects. We propose a promising method of correcting DEA efficiency measures. Despite the multiple advantages DEA offers, the usage of this approach carries with it a number of methodological difficulties. Accounting for multiple factors of efficiency calls for more complex methods, among which the most promising are DMU clustering and calculating local production possibility frontiers. Using regression models for estimate correction requires further study due to possible systematic errors during estimation. A mixture of data correction and DMU clustering together with multi-stage DEA seems most promising at the moment. Analyzing several stages of transforming society’s resources into social welfare will allow for picking out the weak points in a state agency’s work.