The question of the nature of the distributed memory of neural networks is considered. Since the memory capacity of a neural network depends on the presence of feedback in its structure this question requires further study. It is shown that the neural networks without feedbacks can be exhaustively described based on analogy with the algorithms of noiseproof coding. For such networks the use of the term "memory" is not justified at all. Moreover, functioning of such networks obeys the analog of Shannon formula, first obtained in this paper. This formula allows to specify in advance the number of images that a neural network can recognize for a given code distance between them. It is shown that in the case of artificial neural networks with negative feedback it is really justified to talk about a distributed memory network. It is also shown that in this case the boundary between distributed memory of a neural network and information storage mechanisms in such elements as RS-triggers is diffuse. For the given example a specific formula is obtained, which connects the number of possible states of outputs of the network (and, hence, the capacity of its memory) with the number of its elements.
Multivalued logics are becoming one of the most important tools of information technology. They are in great demand for creation of artificial intelligence systems that are close to human intelligence, since the functioning of the latter cannot be reduced to the operations of binary logic. At the same time, the problem of improving the efficiency of using the results of research in multivalued logics, as well as the problem of interpreting variables of multivalued logic, is acute. These problems create certain interdisciplinary barriers and make it difficult to implement the results of research in the field of multivalued logics in other fields of knowledge. It is shown that the problem of interpreting multivalued logic variables can be removed by establishing correspondence with fuzzy logic variables. Improving the efficiency of using of operations of multivalued logics and their variables can be provided by using their close connection to Galois fields. This connection, among other things, makes it possible to reduce any operations of multivalued logics, the number of variables in which is equal to a prime number, to algebraic functions whose arguments take values in Galois fields. This allows, among other things, to eliminate the very cumbersome constructions used in works on multivalued logic and make its apparatus convenient for use in related scientific disciplines in information technology. Direct verification of the adequacy of algorithms based on the use of Galois fields can be carried out by means of radio-electronic circuits, examples of which are presented in the present paper.
It is shown that the implementation of breakthrough progress in artificial intelligence cannot be accomplished without a radical modernization of the methodological framework for research in this area. This upgrade can be performed only with the use of conceptual and methodological apparatus of dialectics. Its consistent application to objects, in either case connected with ideas about the intellect, results in the formulation of the dialectic symmetry principle. The first practical steps for the implementation of the proposed concept in practice are associated with the creation of a new education paradigm, which operates, including ideas that “education” being understood as a public institution, is not reducible to individual learning. Education in modern conditions can and should be viewed primarily as a tool to influence public consciousness, or more precisely, its subsystems.
The interpretation of the category of complex is given on the basis of dialectical positivism, in the framework of which the principle of dialectic symmetry is formulated. It, in turn, is based on the consideration of matter and information as paired dialectic categories. In accordance with this principle, information objects form a hierarchy similar to that which corresponds to different levels of matter organization (mechanical, chemical, biological, social). As “complex”, one should interpret the system that is the medium for the information object at least one level higher than the level related to trivial information (that is, one that is inextricably linked with the object itself). This level is the level corresponding to estranged information (simplifying information about a certain object recorded on another medium).
We present a model of behavior that unifies behavior-based acting and conversational policies for speaking. This model is applied to the domain of air traffic control.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.