On Thu, Mar 12, 2009 at 10:55 AM, Johannes Schindelin <Johannes.Schindelin@xxxxxx> wrote: > On Thu, 12 Mar 2009, John Tapsell wrote: > > 2009/3/11 Ealdwulf Wuffinga <ealdwulf@xxxxxxxxxxxxxx>: > > > What I use is the multiprecision floating point number class. doubles > > > don't seem to be long enough. > > > > Hmm, really really? Sometimes this sort of thing can be fixed by just > > readjusting the formulas. What formulas are you using that require more > > precision than doubles? > > Maybe you could post the formulae instead of forcing people to deduct them > from the source code? I haven't even looked at the source code so a description of the mathematical algorithm would help, but I'll just point out that underflow (in the case of working with probabilities) and overflow (when working with their negated logarithms) is inherent in most multi-step Bayesian algorithms. The only solution is to rescale things as you go so that things stay in a "computable" range. (You're almost never interested in absolute probabilities anyway but rather relative probabilities or, in extreme cases, just the biggest probability, so rescaling isn't losing any useful information.) cheers, dave tweed -- To unsubscribe from this list: send the line "unsubscribe git" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
