We derive and analyze a new pattern recognition approach for automatic modulation recognition of MPSK (2, 4, and 8) signals in broad-band Gaussian noise. Presented method is based on constellation rotation of the received symbols, and a 4th order cumulate of a 1D distribution of the signal's in-phase component. Using Fourier series expansion of this cumulate as a function of the rotation angle, we extract invariant features which are then used in a neural classifier. Discrimination power of the pro- posed set of features is verified through extensive simulations, and the performance of the suggested algorithm is compared to tie maximum-likelihood (ML) classifiers. Corresponding results show that our technique is comparable to the coherent ML classifier and outperforms the non-coherent pseudo- ML method for all considered signal-to-noise ratio (SNR) without the computational overhead of the latter.