Figure 4

Results of applying GA moment (order β = 0.5,1,1.5,2.5, … ,10) and NG measure (MaxNG) compared with FastICA (with g(x)=x³and g(x)=tanh(x) nonlinearities) and the BCA algorithm proposed in [[22]] for the case of n=2 sources and m=2 mixtures. The mixing matrix$\mathbf{A}\in {\mathbb{R}}^{2\times 2}$was generated using independent Gaussian random numbers. We performed a total number of 50 Monte Carlo simulations and we use a total number of T=8,000 samples in each case. On each box, the central mark is the median, the edges of the box are the 25th and 75th percentiles, the whiskers extend to the most extreme data points not considered outliers, and outliers are plotted individually with circles.