		CHANGES IN HANN VERSION 1.2


NEW FEATURES

    o The new function combine() makes predictions combining several
      neural networks possibly optimized with different classes.

    o The new function tune.hann() helps to choose the hyperparameters
      (number of hidden neurons and slope of the activation function).

    o The new function hann() is a wrapper for all types of neural
      nets. The new class "hann" has 'secondary' classes "hann1" or
      "hann3". There are several new methods: summary(), plot(),
      coef(), fitted(), str(), and labels().

    o The optimized networks now include an element $fitted with the
      final signals, and an element $labels with the labels of the
      input classes (particularly useful for combine()).

    o The new function binarize() helps to prepare the binary patterns
      from vectors or matrices of numeric values (e.g., read from
      image files).


BUG FIXES

    o A bug has been fixed in the calculations of gradients of hann3()
      so convergence should be improved and faster.

    o The internal code used to allocate new memory at each iteration:
      this is fixed.


OTHER CHANGES

    o The internal code of hann3() has been optimised so it should be
      at least twice faster.



		CHANGES IN HANN VERSION 1.1


    o Included R_NO_REMAP in prototype_7.c.



		CHANGES IN HANN VERSION 1.0


    o Initial release on CRAN.



		CHANGES IN HANN VERSION 0.1


    o Initial release on GitHub.
