Sifting out the features by pruning: Are convolutional networks the winning lottery ticket of fully connected ones?

04/27/2021 ∙ by Franco Pellegrini, et al. ∙ 9

Pruning methods can considerably reduce the size of artificial neural networks without harming their performance. In some cases, they can even uncover sub-networks that, when trained in isolation, match or surpass the test accuracy of their dense counterparts. Here we study the inductive bias that pruning imprints in such "winning lottery tickets". Focusing on visual tasks, we analyze the architecture resulting from iterative magnitude pruning of a simple fully connected network (FCN). We show that the surviving node connectivity is local in input space, and organized in patterns reminiscent of the ones found in convolutional networks (CNN). We investigate the role played by data and tasks in shaping the architecture of pruned sub-networks. Our results show that the winning lottery tickets of FCNs display the key features of CNNs. The ability of such automatic network-simplifying procedure to recover the key features "hand-crafted" in the design of CNNs suggests interesting applications to other datasets and tasks, in order to discover new and efficient architectural inductive biases.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 5

page 18

page 19

page 21

page 22

page 23

page 24

page 25

Code Repositories

SiftingFeatures

Code for the paper "Sifting out the features by pruning: Are convolutional networks the winning lottery ticket of fully connected ones?"


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.