Visual cognitive algorithms for high-dimensional data and super-intelligence challenges
Department or Administrative Unit
In the long run the cognitive algorithms intend to make super-intelligent machines and super-intelligent humans. This paper presents a technical process to reach specific aspects of super-intelligence that are out of the current human cognitive abilities. These aspects are inabilities to discover patterns in large numeric multidimensional data with a naked eye. This is a long-standing problem in Data Science and Modeling in general. The major obstacle is in human inability to see n-D data by a naked eye and our needs in visualization means to represent n-D data in 2-D losslessly. While these means exist their number and abilities are limited. This paper expands the class of such lossless visual methods, by further developing a new concept of Generalized Shifted Paired Coordinates. It shows the advantages of proposed reversible lossless technique by representing real data and by proving mathematical properties.
Kovalerchuk, B. (2017). Visual cognitive algorithms for high-dimensional data and super-intelligence challenges. Cognitive Systems Research, 45, 95–108. https://doi.org/10.1016/j.cogsys.2017.05.007
Cognitive Systems Research
© 2017 Elsevier B.V. All rights reserved.
This article was originally published in Cognitive Systems Research. The full-text article from the publisher can be found here.
Due to copyright restrictions, this article is not available for free download from ScholarWorks @ CWU.