New answers tagged


I am also wondering about this. It must depend both on convolutional sub-network output size (N) and number of classes (M). Maybe there are some rules of thumbs depending on (N, M). Why 2 dense layers and not, say, 3 or 4 ? Is it better to have all dense layers (except last) the same size ? or decreasing ? or increasing ? or pyramidal ? Is it better to have ...

Top 50 recent answers are included