Structural learning of recurrent RBF networks with M-apoptosis

The apoptosis is an active form of cell death which plays an important role during embryonic development. We propose a unified approach, called M-apoptosis, to the structural learning of recurrent RBF networks. Minkowski norm of the first order derivatives of RBF networks with respect to input variables is added to the cost function for determining the unknown parameters. The parameters are changed so that the MSE and the first order derivatives become small during the learning process. After learning, the input variables of the units with small first order derivatives are deleted.