Publikationsansicht

a (2007)

Abstract
Abstract- In this paper we derive novel algorithms for estimation of regularization parameters and for optimization of neural net architectures based on a validation set. Regularization 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.

Details der Publikation
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.21.142
Quelle http://eivind.imm.dtu.dk/publications/1996/larsen.nnsp96.ps.Z
Mitarbeiter CiteSeerX
Archiv CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Typ text
Sprache Englisch
Verknüpfungen 10.1.1.32.7223, 10.1.1.17.3266, 10.1.1.33.639, 10.1.1.47.8764, 10.1.1.113.737, 10.1.1.29.3833, 10.1.1.20.7156, 10.1.1.29.3425