Orthogonal Transforms in Neural Networks Amount to Effective Regularization

We consider applications of neural networks in nonlinear system identification and formulate a hypothesis that adjusting general network structure by incorporating frequency information or other known orthogonal transform, should result in an efficient neural network retaining its universal properties. We show that such a structure is a universal approximator and that using any orthogonal transform in a proposed way implies regularization during training by adjusting the learning rate of each parameter individually. We empirically show in particular, that such a …

adjusting applications cs.lg cs.ne cs.sy eess.sy general hypothesis identification information network networks neural network neural networks regularization show