SlideWiki | undefined | Learning and Generalization

Small screen detected. You are viewing the mobile version of SlideWiki. If you wish to edit slides you will need to use a larger device.

Learning and Generalization

Neural networks have two important aspects to fulfill:

They must learn decision surfaces from training data, so that training data (and test data) are classified correctly;
They must be able to generalize based on the learning process, in order to classify data sets it has never seen before.

Note that there is an important trade-off between the learning behavior and the generalization of a neural network (called over-fitting)

The better a network learns to successfully classify a training sequence (that might contain errors) the less flexible it is with respect to arbitrary data.

Speaker notes:

There are currently no sources for this slide.