[R] nnet abstol

[Prof Brian Ripley]

>From the help page:

   abstol: Stop if the fit criterion falls below 'abstol', indicating an
           essentially perfect fit.

Now, what the `fit criterion' is depends on the other options that you 
have not told us, but I don't see MSE mentioned anywhere on that help 
page, and I do see `least-squares'.

On Wed, 9 Mar 2005, Kemp S E (Comp) wrote:

> Hi,
>
> I am using nnet to learn transfer functions. For each transfer function 
> I can estimate the best possible Mean Squared Error (MSE). So, rather 
> than trying to grind the MSE to 0, I would like to use abstol to stop 
> training once the best MSE is reached.
>
> Can anyone confirm that the abstol parameter in the nnet function is the 
> MSE, or is it the Sum-of-Squares (SSE)?

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595