The main advantage of induction cooking is the pan heating without thermal inertia.However to obtain best efficiency, it is essential to have an inductor geometry that gives ahomogeneous temperature on the pan bottom. In this paper, we will first model the magnetothermal phenomena of the system by a finite element method (FEM) in order to determine thedistribution of temperature on the pan bottom taking into consideration the nonlinearity of thesystem. This study shows that the temperature is not homogeneously distributed. Then, in the aim tohave homogeneous temperature distribution in the pan bottom, we propose an inductor structurewith four throats containing the coils and we will use Neural Networks to determine the optimalthroats distribution and their dimensions. The optimized structure permits us to achieve our goal.