Note that the weighted decoding rule with is equivalent to the simple maximum rule in (8).
People use different methods such as majority voting, weighted voting, sum rule, mean rule, product rule, maximum rule, minimum rule, correlation and mutual information to build the combiner.
From Figure 7, we can see that the maximal average pooling rules (Rules 1 and 2) perform better than the trial maximum (Rule 3), average pooling rules (Rule 4) and weighted pooling rules (Rules 5 and 6).
As can be seen, the weighted decoding rule performs better than the simple maximum rule since the former takes into account the effect of the other decomposed -tuples on localization accuracy by adjusting their weights.
Kittler et al. [19] experimented with several fusion techniques for face and voice, including sum, product, minimum, median, and maximum rules, and they found that sum rule outperforms the others.
To decode, a scalar correlation is computed and the final decision is computed with a maximum likelihood decision rule.
As in Fredriksson et al. 2013, the Browning and Heinesen 2007 study relies on the exogenous variation provided by a maximum class size rule.
In the final step, the classification maps of each individual scale are combined with a maximum vote decision rule and the final classification map is obtained.
General expressions are mathematically derived for the maximum differences between graphical indices and sound insulation in two cases: a maximum allowable sum rule for unfavourable deviations, and a combination for restriction of the maximum single deviation.
De Paola and Scoppa (2011) exploit exogenous variations in class size determined by a maximum class size rule introduced by the 2001 Italian university reform and find negative effects on student achievement.
