>After training, we could take advantage of the structure to remove ~80% of the weights in topographic layers without sacrificing performance
This is really interesting to me. Is it that the structure clustered the neurons in such a way that they didn't need to be weighted because their function were grouped by similar black box properties?
This is really interesting to me. Is it that the structure clustered the neurons in such a way that they didn't need to be weighted because their function were grouped by similar black box properties?