“…Data-driven modeling has become a powerful technique in different areas of engineering, such as industrial data analysis (Luo et al, 2015;Li et al, 2017), circuits analysis and design (Ceperic et al, 2014;Shokouhifar & Jalali, 2015;Zarifi et al, 2015), signal processing (Yang et al, 2005;Volaric et al, 2017), empirical modeling (Gusel & Brezocnik, 2011;Mehr & Nourani, 2017), system identification (Guo & Li, 2012;Wong et al, 2008), etc. For a concerned data-driven modeling problem with n input variables, we aim to find a performance function f * : R n → R that best explains the relationship between input variables x = x 1 x 2 · · · x n T ∈ R n and the target system (or constrained system) based on a given set of sample points S = x (1) x (2) · · · x (N ) T ∈ R N ×n .…”