A2DE achieves highly accurate classification by averaging over all of a small space of alternative naive-Bayes-like models that have weaker (and hence less detrimental) independence assumptions than naive Bayes

The resulting algorithm is computationally efficient while delivering highly accurate classification on many learning tasks.

For more information, see

Webb, Geoffrey I., Boughton, Janice, Zheng, Fei, Ting, Kai Ming, Salem, Houssam (2012).Learning by extrapolation from marginal to full-multivariate probability distributions: decreasingly naive {Bayesian} classification.

Machine Learning.86(2):233-272.

Further papers are available at

http://www.csse.monash.edu.au/~webb/.

Use m-estimate for smoothing base probability estimates witha default of 1 (m value can changed via option -M).Default mode is non-incremental that is probabilites are computed at learning time.

An incremental version can be used via option -I.

Default frequency limit set to 1.

(based on WEKA 3.7)

For further options, click the 'More' - button in the dialog.

All weka dialogs have a panel where you can specify classifier-specific parameters.