Family of Cascade-correlation Learning Algorithm

A Genetic Cascade-Correlation Learning Algorithm∗

Gradient descent techniques such as back propagation have been used effectively to train neural network connection weights; however, in some applications gradient information may not be available. Biologically inspired genetic algorithms provide an alternative. Unfortunately, early attempts to use genetic algorithms to train connection weights demonstrated that exchanging genetic material betwe...

Simplified cascade-correlation learning

Learning with limited numerical precision using the cascade-correlation algorithm

A key question in the design of specialized hardware for simulation of neural networks is whether fixed-point arithmetic of limited numerical precision can be used with existing learning algorithms. An empirical study of the effects of limited precision in cascade-correlation networks on three different learning problems is presented. It is shown that learning can fail abruptly as the precision...

The Cascade-Correlation Learning Architecture

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 w...

Experiments with the Cascade-Correlation Algorithm

1 2 3 This paper describes a series of experiments with the cascade-correlation algorithm (CCA) and some of its variants on a number of real-world pattern classi cation tasks. Some of these experiments investigate the e ect of di erent design parameters on the performance of CCA (in terms of number of training epochs and classi cation accuracy on the test data). Parameter settings that consiste...