Feature selection is a widely studied technique whose goal is to reduce the dimensionality of the problem by removing irrelevant features. It has multiple benefits, such as improved efficacy, efficiency and interpretability of almost any type of machine learning model. Feature selection techniques may be divided into three main categories, depending on the process used to remove the features known as Filter, Wrapper and Embedded. Embedded methods are usually the preferred feature selection method that efficiently obtains a selection of the (...) most relevant features of the model. However, not all models support an embedded feature selection that forces the use of a different method, reducing the efficiency and reliability of the selection. Neural networks are an example of a model that does not support embedded feature selection. As neural networks have shown to provide remarkable results in multiple scenarios such as classification and regression, sometimes in an ensemble with a model that includes an embedded feature selection, we attempt to embed a feature selection process with a general-purpose methodology. In this work, we propose a novel general-purpose layer for neural networks that removes the influence of irrelevant features. The Feature-Aware Drop Layer is included at the top of the neural network and trained during the backpropagation process without any additional parameters. Our methodology is tested with 17 datasets for classification and regression tasks, including data from different fields such as Health, Economic and Environment, among others. The results show remarkable improvements compared to three different feature selection approaches, with reliable, efficient and effective results. (shrink)

Kuznet︠s︡ov, I. V. Kategorii︠a︡ prichinnosti i ee poznavatelʹnoe znachenie.--Shali︠u︡tin, S. M. Ob otrazhenii kak obshchem svoĭstve materii.--I︠U︡rgelenas, D. I. Teorii︠a︡ otrazhenii︠a︡ i poni︠a︡tie informat︠s︡ii.--Korneeva, A. I. Vozrastai︠u︡shchai︠a︡ rolʹ logicheskogo myshlenii︠a︡ v poznanii mira.--Klimashevskiĭ, G. Teoretiko-poznavatelʹnai︠a︡ rolʹ myslennogo ėksperimenta v fizike.-- Podosetnik, V. M. Gnoseologicheskoe znachenie faktov v poznanii obshchestvennykh i︠a︡vleniĭ.

The article devoted to the analysis of theoretical and conceptual developments of the Russian Social Democrats in the emigrant period. The authors note that the concept of democratic socialism, which began to be formed in 1917, was considerably amended and deepened when the Mensheviks created a new party program developed in 1922-1924. The significance of this program of the RSDLP is practically not evaluated in the science literature. In the analysis of Soviet historiography, the authors of the article outlined the (...) lack of attention to the projects of the Mensheviks in emigration, as the researchers insisted on the collapse of the RSDLP in post-October period. Some of modern researchers are highly skeptical about the intellectual developments of the Russian Social Democrats after the events of October 1917. However, the authors identified a number of innovative elements in the projects of the Mensheviks in this time. The new party program is an original stage in the formation of the concept of post-revolutionary development of Russia. In the course of the inner-party discussion, the differences in assessing the degree of Russia’s readiness for socialist transformation, as well as the Bolshevik experiment with various internal political trends, were sharply denoted. The article analyzes the positions of representatives of the official Mensheviks and the right wing of the party. The authors acknowledge the significant transformation of the political attitudes of the Mensheviks, pointing to some delusional and utopian nature of a number of program theses. (shrink)

By using a tomographic approach to quantum states, we rise the problem of nonlocality within a single particle (single degree of freedom). We propose a possible way to look for such e®ects on a qubit. Although a conclusive answer is far from being reached, we provide some re°ections on the foundational ground.

Alison Gopnik and Andrew Meltzoff have argued for a view they call the 'theory theory': theory change in science and children are similar. While their version of the theory theory has been criticized for depending on a number of disputed claims, we argue that there is a fundamental problem which is much more basic: the theory theory is multiply ambiguous. We show that it might be claiming that a similarity holds between theory change in children and (i) individual scientists, (ii) (...) a rational reconstruction of a Superscientist, or (iii) the scientific community. We argue that (i) is false, (ii) is non-empirical (which is problematic since the theory theory is supposed to be a bold empirical hypothesis), and (iii) is either false or doesn't make enough sense to have a truth-value. We conclude that the theory theory is an interesting failure. Its failure points the way to a full, empirical picture of scientific development, one that marries a concern with the social dynamics of science to a psychological theory of scientific cognition. (shrink)

Known pedagogical concept of I. P. Ivanov considered and analyzed from the perspective of two sciences: psychology and cybernetics. It is shown that the basic principles of pedagogy common concern based implicitly and may be explained in particular on the fundamental positions of the two classical disciplines (Ashby laws, the second principle, the initial threshold of complexity, etc. in cybernetics and cultural-historical and activity approach in psychology).

Написанная доступным языком, книга представляет интерес не только для специалистов в области экономики, культуры, политики, но и для широкого круга читателей.

New trends in the economic systems management in the context of modern global challenges: collective monograph / scientific edited by M. Bezpartochnyi, in 2 Vol. // VUZF University of Finance, Business and Entrepreneurship. – Sofia: VUZF Publishing House “St. Grigorii Bogoslov”, 2020. – Vol. 1. – 309 p.

This paper reports the introduction of electronic handsets, like those used on the television show 'Who Wants To Be A Millionaire?' into the teaching of philosophical logic. Logic lectures can provide quite a formidable challenge for many students, occasionally to the point of making them ill. Our rationale for introducing handsets was threefold: to get the students thinking and talking about the subject in a public environment; to make them feel secure enough to answer questions in the lectures because the (...) system enabled them to do this anonymously; and to build their confidence about their learning by their being able to see how they were progressing in relation to the rest of the students in the class. We have achieved all of these and more. Our experience has revealed that the use of handsets encourages a more dynamic form of student interaction in an environment - the lecture - that can, in the wrong hands, be utterly enervating, but they also provide an opportunity for the lecturer to respond to students' difficulties at the time when they really matter. In this paper, we discuss our case of rapid adoption, our grounds for judging it a success, and what that success seems to have depended on. (shrink)

Microbiologists are transitioning from the study and characterization of individual strains or species to the profiling of whole microbiomes and microbial ecology. Equipped with high-throughput methods for studying the taxonomic and functional characteristics of diverse samples, they are just beginning to encounter the conceptual, theoretical, and experimental problems of comparing taxonomy to function, and extracting useful measures from such comparisons. Although still unresolved, these problems are well studied in macro-ecology and are reiterated here as an historical precautionary for microbial ecologists. (...) Beyond expected and unresolved terminological vagueness, we argue that assessments and comparisons of taxonomic and functional profiles in micro-ecology suffer from theoretically unresolvable arbitrariness and ambiguities. We divide these into problems of scale, individuation, and commensurability. We argue that there is no technically/theoretically “correct” scale, individuation, or comparison of taxonomy and function, but there are nonetheless better and worse methodologies for profiling. (shrink)

Context: Distributed language and interactivity are central members of a set of concepts that are rapidly developing into rigorous, exciting additions to 4E cognitive science. Because they share certain assumptions and methodological commitments with enactivism, the two have sometimes been confused; additionally, while enactivism is a well-developed paradigm, interactivity has relied more on methodological development and on a set of focal examples. Problem: The goal of this article is to clarify the core conceptual commitments of both interactivity-based and enactive approaches (...) to cognitive science by contrasting the two and highlighting their differences in assumptions, focus, and explanatory strategies. Method: We begin with the shared commitments of interactivity and enactivism - e.g., antirepresentationalism, naturalism, interdisciplinarity, the importance of biology, etc. We then give an overview of several important varieties of enactivism, including sensorimotor and anti-representationalist enactivism, and then walk through the history of the “core” varieties, taking care to contrast Maturana’s approach with that of Varela and the current researchers following in Varela’s footsteps. We then describe the differences between this latter group and interactivity-based approaches to cognitive science. Results: We argue that enactivism’s core concepts are explanatorily inadequate in two ways. First, they mis-portray the organization of many living systems, which are not operationally closed. Second, they fail to realize that most epistemic activity depends on engagement with non-local resources. Both problems can be dealt with by adopting an interactivity-based perspective, in which agency and cognition are fundamentally distributed and involve integration of non-local resources into the local coupling of organism and environment. Implications: The article’s primary goal is theoretical clarification and exposition; its primary implication is that enactive concepts need to be modified or extended in some way in order to explain fully many aspects of cognition and directed biological activity. Or, read another way, the article’s primary implication is that interactivity already provides a rich set of concepts for doing just that, which, while closely allied with enactivism in several ways, are not enactivist concepts. Constructivist content: The article consists entirely of a comparison between two constructivist fields of theory. Key Words: Interactivity, enactivism, distributed language, radical embodied cognitive science, ecological psychology, autonomy. (shrink)

In this paper, we argue that there are reasons to believe that an implicit bias for normalcy influences what are considered medically necessary treatments in psychiatry. First, we outline two prima facie reasons to suspect that this is the case. A bias for ‘the normal’ is already documented in disability studies; it is reasonable to suspect that it affects psychiatry too, since psychiatric patients, like disabled people, are often perceived as ‘weird’ by others. Secondly, psychiatry's explicitly endorsed values of well-being (...) and function are hard to measure directly, which is why we see simpler box-ticking conceptions of recovery used in large research studies. This need not be problematic, but might lead to researchers and clinicians focusing too much on treatments that promote easy-to-measure proxies for recovery, instead of what actually matters to psychiatric patients themselves. Next, we provide examples of treatments and treatment decisions within two areas – self-injury and psychosis – which are hard to explain unless we assume that an implicit and harmful normalcy bias is at work. We conclude with some suggestions for clinicians and future research. (shrink)

Upshot: We agree with commenters that enactivism incorporates a broad variety of methodologies, metaphysical stances, concepts, and investigative approaches, and that this is a good thing. However, we remain concerned that autonomy and sense-making are problematic concepts for post-Varelian enactivism, and that they form the foundations of a conceptual framework that may hamper the development of effective explanations for cognitive activity, as well as the paradigmatic aspirations of this particular enactivist approach.