Constraints on fNL from Wilkinson Microwave Anisotropy Probe 7-year data using a neural network classifier.

ABSTRACT We present a multiclass neural network (NN) classifier as a method to measure non-Gaussianity, characterized by the local non-linear coupling parameter f_NL, in maps of the cosmic microwave background (CMB) radiation. The classifier is trained on simulated non-Gaussian CMB maps with a range of known f_NL values by providing it with wavelet coefficients of the maps; we consider both the HEALP ix wavelet (HW) and the spherical Mexican hat wavelet (SMHW). When applied to simulated test maps, the NN classifier produces results in very good agreement with those obtained using standard χ² minimization. The standard deviations of the f_NL estimates for Wilkinson Microwave Anisotropy Probe¹ like simulations were σ= 22 and 33 for the SMHW and the HW, respectively, which are extremely close to those obtained using classical statistical methods in Curto et al. and Casaponsa et al. Moreover, the NN classifier does not require the inversion of a large covariance matrix, thus avoiding any need to regularize the matrix when it is not directly invertible, and is considerably faster. [ABSTRACT FROM AUTHOR]