The Cascade-Correlation Learning Architecture

 

Scott E. Fahlman and Christian Lebiere

 

Abstract

 

Cascade-Correlation is a new architecture and supervised learning algorithm for artificial neural networks.  Instead of just adjusting the weights in a network of fixed topology, Cascade-Correlation begins with a minimal network, then automatically trains and adds new hidden units one by one, creating a multi-layer structure.  Once a new hidden unit has been added to the network, its input-side weights are frozen.  This unit then becomes a permanent feature-detector in the network, available for producing outputs or for creating other, more complex feature detectors.

 

The Cascade-Correlation architecture has several advantages over existing algorithms: it learns very quickly, the network determines its own size and topology, it retains the structures it has built even if the training set changes, and it requires no back-propagation of error signals through the connections of the network.