These notes give the changes since the version of 1998-09-01.  A
release dated 1999-02-20 was briefly available.  The only thing
substantial change in this release is that the bug with the "delta"
option noted below has been fixed.  There are also some very minor
documentation updates and a fix to make-clean.

Changes in this version:

1) Examples of neural network models for survival analysis have been
   added.  Some bugs in this part of the software have been fixed too.

Bug fixes.

A serious bug with the "delta" option for Gaussian process models has
been fixed.  This bug was present in version from 1998-08-02 until
this version.

Some bugs regarding the survival analysis models have been fixed.  A
problem that arose when automatic standardization was used for a
variable that always had the same value in the training data has been
fixed.  The computation of the likelihood for binary models is now
more bullet-proof, and should avoid floating point overflow even in
extreme cases.  Make-clean now knows to remove mc-ais.

Known bugs and other deficiencies.

1) The facility for plotting quantities using "plot" operations in xxx-mc
   doesn't always work for the first run of xxx-mc (before any
   iterations exist in the log file).  A work-around is to do a run of
   xxx-mc to produce just one iteration before attempting a run of
   xxx-mc that does any "plot" operations.

2) The CPU time features (eg, the "k" quantity) will not work correctly
   if a single iteration takes more than about 71 minutes.

3) The latent value update operations for Gaussian processes may recompute 
   the inverse covariance matrix even when an up-to-date version was 
   computed for the previous Monte Carlo operation.

4) Covariance matrices are stored in full, even though they are symmetric,
   which sometimes costs a factor of two in memory usage.

5) The "p" option of net-pred isn't allowed for survival models with
   piecewise-constant hazard.  There's no big reason for this - I just
   haven't gotten around to it.