Cascade Correlation: Derivation of a More Numerically Stable Update Rule George John Computer Science Dept. Stanford University Stanford, CA 94305 gjohn@cs.stanford.edu We discuss the weight update rule in the Cascade Correlation neural net learning algorithm. The weight update rule implements gradient descent optimization of the correlation between a new hidden unit's output and the previous network's error. We present a derivation of the gradient of the correlation function and show that our resulting weight update rule results in slightly faster training. We also show that the new rule is mathematically equivalent to the one presented in the original Cascade Correlation paper and discuss numerical issues underlying the difference in performance. Since a derivation of the Cascade Correlation weight update rule was not published, this paper should be useful to those who wish to understand the rule. Citation: George H. John. Cascade Correlation: Derivation of a More Numerically Stable Update Rule. In _International Conference on Neural Networks_, pages 1126-1129. Perth, Western Australia, IEEE Press, 1995.