Design and regularization of neural networks: the optimal use of a validation set
Jan Otto Larsen, Lars Kai Hansen, Claus Svarer, Mattias Ohlsson · 2002
We derive novel algorithms for estimation of regularization parameters and for optimization of neural net architectures based on a validation set. Regularisation parameters are estimated using an iterative gradient descent scheme. Architecture optimization is performed by approximative combinatorial search among the relevant subsets of an initial neural network architecture by employing a validation set based optimal brain damage/surgeon (OBD/OBS) or a mean field combinatorial optimization approach. Numerical results with linear models and feed-forward neural networks demonstrate the viability of the methods.