ISSN :2582-9793
Vladik Kreinovich
Adv. Artif. Intell. Mach. Learn., 2 (3):456-468
Vladik Kreinovich : Department of Computer ScienceUniversity of Texas at El Paso, El Paso, Texas, USA
DOI: 10.54364/AAIML.2022.1130
Article History: Received on: 04-Sep-22, Accepted on: 04-Oct-22, Published on: 30-Sep-22
Corresponding Author: Vladik Kreinovich
Email: vladik@utep.edu
Citation: Vladik Kreinovich (2022). Invariance-Based Approach Explains Empirical Formulas from Pavement Engineering to Deep Learning. Adv. Artif. Intell. Mach. Learn., 2 (3 ):456-468
In many application areas, there are effective empirical formulas that
need explanation. In this paper, we focus on two such challenges: neural networks, where a so-called softplus activation function is known to be
very efficient, and pavement engineering, where there are empirical formulas describing the dependence of the pavement strength on the properties
of the underlying soil. We show that similar scale-invariance ideas can explain both types of formulas – and, in the case of pavement engineering,
invariance ideas can lead to a new formula that combines the advantages
of several known ones.