Approximating with radial basis functions: An evolutionary approach (Q2759581)

The Radial Basis Function (RBF) method is one of the method for solving the real multivariable interpolation problem, i.e., the problem of finding a function \(f\) from \(\mathbb{R}^n\) to \(\mathbb{R}\) satisfying the conditions \(f(X_i)=y_i\), \(i=1,2,\dots,n\), where \(X_i\), \(i=1,\dots,N\) are \(N\) vectors in \(\mathbb{R}^n\) and \(y_i\in N\) real numbers. The RBF method consists on the construction of the function \(f\) of the form \(f(X)=\sum_{i=1}^N c_i h(\|X-X_i\|)\), where \(h\) is a continuous function from \(\mathbb{R}^+\) to \(\mathbb{R}\) and \(\|\cdot\|\) is a norm in \(\mathbb{R}^n\). In the present paper the authors used these RBF to built an evolutionary methodology for the generation of parsimonious approximation models calculated from experimental data.NEWLINENEWLINEFor the entire collection see [Zbl 0970.00036].