Intelligent Information Systems
-
Lecture 10 - Multi-Layer Perceptrons
First page
Back
Continue
Last page
Overview
Graphics
Problems with MLP
Choosing the number of hidden nodes
how many are enough?
Usually, the number of connections in the network should be less than the number of training examples
As number of connections approaches the number of training examples, generalisation decreases
Tweet
Maintained by Dr Michael J. Watts (
mike.watts.net.nz
).