Comparison of generalization in multi-layer perceptrons with the log-likelihood and least-squares cost functions
M.J.J. Holt · 2003
The log likelihood cost function is discussed as an alternative to the least-squares criterion for training feedforward neural networks. An analysis is presented which suggests how the use of this function can improve convergence and generalization. Tests on simulated data using both training algorithms provide evidence of improved generalization with the log likelihood cost function.>