Re: Very different results in 2 weka SMO versions?

No, they shouldn't be viewed that way.

Cheers,
Eibe

On Aug 31, 2005, at 5:41 PM, yee seng chan wrote:

> Eibe, thanks for the prompt reply! I've 1 more question below:
>  
>> The reason is that the old version used the standard sigmoid function
>> (i.e. without any fitting) to transform the SVM's output into [0,1]. 
> So this sigmoid function is not parameterized (i.e. not fitted to the 
> training data). In this case, can the real numbers output from this 
> old SMO version be considered to be proper probability estimates?
>  
> Thanks,
> Yee Seng.
>
>> In
>> default mode, the new version computes a "probability" based on the
>> number of votes each class receives in pairwise classification. To get
>> proper probability estimates you need to turn on the logistic model
>> option, which fits a logistic model (i.e. parametrized sigmoid) to the
>> output of each SVM in the pairwise classifier and then performs
>> pairwise coupling.
>>
>> Cheers,
>> Eibe
>>
>> On Aug 31, 2005, at 3:32 AM, yee seng chan wrote: