Learning in two-layered networks with correlated examples

Unspecific Reinforcement Learning in One and Two - layered Networks

The dynamics of on-line learning of a perceptron with a learning rule based on the Hebb rule with “delayed” unspecific reinforcement is studied for a special case of the feedback definition. This learning algorithm combines an associative and a reinforcement step and the relevant learning parameter λ represents the ratio of the associative to the reinforcement step. For given initial conditions...

Learning from examples in large neural networks.

A statistical mechanical theory of learning from examples in layered networks at finite temperature is studied. When the training error is a smooth function of continuously varying weights the generalization error falls off asymptotically as the inverse number of examples. By analytical and numerical studies of single-layer perceptrons we show that when the weights are discrete the generalizati...

Accelerated Learning in Layered Neural Networks

Abst ract . Learning in layered neu ral networks is posed as the minimizat ion of an error function defined over the training set. A probabilist ic interpretation of the target act ivities suggests the use of relat ive ent ropy as an error measure. We investigate t he merits of using this error function over t he traditional quad ratic function for gradient descent learni ng. Comparative numeri...

Two Approximations to Learning from Examples

Classifiers Based on Two-Layered Learning

In this paper we present an exemplary classifier (classification algorithm) based on two-layered learning. In the first layer of learning a collection of classifiers is induced from a part of original training data set. In the second layer classifiers are induced using patterns extracted from already constructed classifiers on the basis of their performance on the remaining part of training dat...