A Note on Representational Understanding

Antal Jakovác; András Telcs

doi:10.3390/e24091313

A Note on Representational Understanding

Entropy (Basel). 2022 Sep 17;24(9):1313. doi: 10.3390/e24091313.

Authors

Antal Jakovác¹, András Telcs^{1

2

3}

Affiliations

¹ Department of Computational Sciences, Wigner Research Centre for Physics, H-1121 Budapest, Hungary.
² Department of Computer Science and Information Theory, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, H-1111 Budapest, Hungary.
³ Department of Quantitative Methods, Faculty of Business and Economics, University of Pannonia, H-8200 Veszprém, Hungary.

Abstract

In this paper, we explore a new approach in which understanding is interpreted as a set representation. We prove that understanding/representation, finding the appropriate coordination of data, is equivalent to finding the minimum of the representational entropy. For the control of the search for the correct representation, we propose a loss function as a combination of the representational entropy, type one and type two errors. Computational complexity estimates are presented for the process of understanding and using the representation found.

Keywords: coordinate systems; data representation; entropy; first and second error.

Grants and funding

A.T. was partially supported by the Ministry of Innovation and Technology NRDI and the National Research, Development and Innovation Office, within the framework of the MILAB, Artificial Intelligence National Laboratory of Hungary and by the Hungarian Brain Research Program (2017-1.2.1-NKP-2017-00002). A.J. had a support from the Ministry of Innovation and Technology NRDI Office within the framework of the MILAB, Artificial Intelligence National Laboratory Program and the Hungarian Research Fund NKFIH (OTKA) under contract No. K123815.