Graph Structure of Neural Networks: Difference between revisions

From statwiki
Jump to navigation Jump to search
No edit summary
Line 5: Line 5:
= Introduction =
= Introduction =


= Related Work =  
= Major Conclusions =
 
(1) graph structure of neural networks matters;
 
(2) a “sweet spot” of relational graphs lead to neural networks with significantly improved predictive performance;
 
(3) neural network’s performance is approximately a smooth function of the clustering coefficient and average path length of its relational graph;
 
(4) our findings are consistent across many different tasks and datasets;
 
(5) top architectures can be identified efficiently;
 
(6) well-performing neural networks have graph structure surprisingly similar to those of real biological neural networks.


= Section 1 =
= Section 1 =

Revision as of 15:35, 10 November 2020

Presented By

Xiaolan Xu, Robin Wen, Yue Weng, Beizhen Chang

Introduction

Major Conclusions

(1) graph structure of neural networks matters;

(2) a “sweet spot” of relational graphs lead to neural networks with significantly improved predictive performance;

(3) neural network’s performance is approximately a smooth function of the clustering coefficient and average path length of its relational graph;

(4) our findings are consistent across many different tasks and datasets;

(5) top architectures can be identified efficiently;

(6) well-performing neural networks have graph structure surprisingly similar to those of real biological neural networks.

Section 1

Section 2

Section 3

Conclusion

Critique