search

RobertCsordas / linear_layer_as_attention

The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention".
16 stars 1 forks source link

NN layer #1

Open zzw-zwzhang opened 2 years ago

zzw-zwzhang commented 2 years ago

Thanks for the interesting work.

Why you only use NN with two FC layers, how about the results on large scaled network?