The dynamics of an-line learning is investigated for structurally unrealizable tasks in the context of two-layer neural networks with an arbitrary number of hidden neurons. Within a statistical mechanics framework a closed set of differential equations describing the learning dynamics can be derived, for the general case of unrealizable isotropic tacks. In the asymptotic regime one can solve the dynamics analytically in the limit of a large number of hidden neurons, providing an analytical expression for the residual generalization error, the optimal and critical asymptotic training parameters, and the corresponding prefactor of the generalization error decay
On-line learning of unrealizable tasks
SCARPETTA, Silvia;
1999-01-01
Abstract
The dynamics of an-line learning is investigated for structurally unrealizable tasks in the context of two-layer neural networks with an arbitrary number of hidden neurons. Within a statistical mechanics framework a closed set of differential equations describing the learning dynamics can be derived, for the general case of unrealizable isotropic tacks. In the asymptotic regime one can solve the dynamics analytically in the limit of a large number of hidden neurons, providing an analytical expression for the residual generalization error, the optimal and critical asymptotic training parameters, and the corresponding prefactor of the generalization error decayI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
