In this article, a brain-inspired winner-take-all emotional neural network (WTAENN) architecture is proposed and then the universal approximation property for this kind of architecture is proved. WTAENN is a single layered feedforward neural network that benefits from the excitatory, inhibitory, and expandatory neural connections as well as the winner-take-all (WTA) competitions in the human brain's nervous system. The universal approximation capability of the proposed architecture is illustrated on two example functions and then applied to several competing benchmark problems such as curve fitting, pattern recognition, classification and prediction. In particular, it is tested on twelve UCI classification datasets, a facial recognition problem, three real world prediction problems (2 chaotic time series of geomagnetic activity indices and wind farm power generation data), two synthetic case studies with constant and nonconstant noise variance as well as k-selector and linear programming problems. The results indicate the general applicability and often superiority of the approach in terms of higher accuracy and lower model complexity, especially where low computational complexity is imperative.

Keywords