ANN1_DOC.TXT-- XTAL Version 5 Regression Package                Comments regarding the ANN source code      The source code used for ANN1 regression is derived from thesoftware supplied with the book "Practical Neural Network Recipes inC++" by Timothy Masters and published 1993 by Academic Press.  Theoriginal source was written to run on an IBM PC but was modified sothat it could be compiled to run on a Sun Sparcstation.  It will runthe same as described in the book with two exceptions: (1) The escapekey will not interrupt training as in the IBM version.  (2) The newversion is case sensitive with respect to filenames since Unixfilenames are case sensitive but DOS is not.     Beware when using this module standalone , since although itbehaves as described in the book it does not operate as it is usedwith XTAL.  In particular, XTAL rescales the response variable so thatit falls in the range .1 to .9 as required by the original software.The book is therefore absolutely necessary as a reference if usingANN1 separate from the XTAL package.     This code was compiled with the "g++" compiler from the FreeSoftware Foundation.  It does not compile correctly with the Suncompiler available on the Sun Sparcstations here at the U of M.