the relationship between the number of filters/kernels and the number of feature maps

2017-11-30 02:10:11

The above image is from "Deep Learning Tutorial" by Yann LeCun and Marc'Aurelio Ranzato (see pages 73 and 81).

I don't understand why 64 kernels (from the input to layer 1) produce 64 feature maps while 4096 kernels (layer 2 to layer 3) give 256 feature maps.