Relationship between the number of elements in constraint satisfaction problems and the computation time of HNN

Takumi GENKA; Kenya JIN'NO

doi:10.1587/nolta.13.282

Special Section on Nonlinear Science Workshop on the Journal

Relationship between the number of elements in constraint satisfaction problems and the computation time of HNN

Author information

Keywords: neural networks, constraint satisfaction problem, computation time, computation complexity, ordinary differential equation

JOURNAL FREE ACCESS

2022 Volume 13 Issue 2 Pages 282-287

DOI https://doi.org/10.1587/nolta.13.282

Details

Abstract

In this paper, we aim to clarify the computational complexity of artificial neural networks. We investigate the computational complexity of hysteresis neural networks (HNN) for solving constraint satisfaction problems. We confirm that the amount of computation is proportional to the logarithm of the size of the problem.

Corresponding author

Register with J-STAGE for free!