LIMIT

Keyword of Float Type

Indicate normalized RMSE error to stop neural network training. A neural network calculation is stopped if RMSE error is less than value of this keyword.

The RMSE is defined as SQRT(SUM{(Ycalc-Yexp)^2}/n), where Ycalc is calculated, Yexp is normalized target value, and SUM is over n values. The Ycalc values are calculated by simple average over all neural network predictions in the ENSEMBLE. The termination of program is done if RMSE error calculated for the learning set is less than LIMIT.

Copyright 2001 -- 2009 http://www.vcclab.org. All rights reserved.