Robust spherical clustering as mixed integer optimization problem and its gradient network solution

Support vector based spherical clustering is described as an optimization problem posed in the input space where the cluster indicators are also considered as variables. It is attempted to find the robust clustering by taking the objective function of the optimization problem as the energy function of the gradient network. The proposed method is an extension of the authors' work which formulated the clustering problem as a mixed integer optimization by considering the cluster indicators and centers as variables.