The Research of Penalty Functions Based on Neural Networks
The penalty functions are introduced in the negative correlation learning for finding a neural network in an ensemble. It is based on the average output of the ensemble. The idea of penalty function based on the average output is to make each individual network has the different output value to that of the ensemble on the same input. Experiments on a classification task show how the negative correlation learning generates a neural network with penalty functions.
Helen Zhang and David Jin
Y. Ding et al., "The Research of Penalty Functions Based on Neural Networks", Applied Mechanics and Materials, Vols. 63-64, pp. 205-208, 2011