ChangeLog: ANN Toolbox --- for Scilab
           ==========================

=====================================================================
From 0.4.2.3 -> 0.4.2.4 :

- compatibility with Scilab 5.3.0
(Allan CORNET , DIGITEO , 2010)
=====================================================================
From 0.4.2.2 -> 0.4.2.3 :

- compatibility with Scilab 5.2.0
(Allan CORNET , DIGITEO , 2009)
=====================================================================
From 0.4.2.1 -> 0.4.2.2 :

- remove some hardcoded paths
(Allan CORNET , DIGITEO , 2008)
=====================================================================
From 0.4.2 -> 0.4.2.1 :

- Adjustments for Scilab 5.x
macros and help updated
uses standard architecture of toolboxes for scilab 5.0
(Allan CORNET , INRIA , 2008)

=====================================================================
From 0.4.1 -> 0.4.2
Minor adjustments for Scilab 2.6:
- install.sh script which will install/uninstall the toolbox
  (system-wide or in selected dir)
- manual updates (macros change, contents unchanged)

From 0.4 -> 0.4.1

Minor adjustments for the new Scilab 2.5:
  - new Makefile
  - README updated

=====================================================================

From 0.3 -> 0.4

Function names have been rationalized to a more suitable nomenclature.
Discrete time loops are now performed inside training engines.
Some algorithms added.

WHAT YOU HAVE TO DO TO CONVERT YOUR OLD SCRIPTS:
 - rename the functions according to the new nomenclature.
 - some training engines now perform the discrete time loops inside,
   so they require a new parameter T and external looping have to be
   removed. Also note that the format of optional ex parameter have also
   changed in order to acomodate this.

=====================================================================

From 0.2x -> 0.3

This toolkit now uses hypermatrices available only on Scilab 2.4
and upward. This will make possible to easily add future algorithms.
Also: the patterns are now represented by column vectors and weight
matrices are as one would expect, i.e. as they are currently used
in main ANN literature.

For these reasons scripts written for previous version(s) of this toolkit
will not work on this one. I apologies for inconveniences. The introduction
of hypermatrices in Scilab 2.4 will (PROBABLY) make unnecessary any other
major changes in future versions of this toolkit (from the user's scripts
point of view).

WHAT YOU HAVE TO DO TO CONVERT YOUR OLD SCRIPTS:
  - transpose the inputs and targets, e.g. x=x'
    and nothing else if you don't touch the weight matrix;
  - if you manipulated the weight matrix then convert that part to the
    new format of W, see the man pages for details.
