Difference between revisions of "Graph Structure of Neural Networks"

From statwiki
Jump to: navigation, search
(Related Work)
Line 5: Line 5:
 
= Introduction =
 
= Introduction =
  
= Major Conclusions =
+
= Relational Graph =
 +
 
 +
= Parameter Definition =
 +
 
 +
(1) Clustering Coefficient
 +
 
 +
(2) Average Path Length
 +
 
 +
= Experimental Setup (Section 4 in the paper) =
 +
 
 +
= Major Conclusions (Section 5 in the paper) =
  
 
(1) graph structure of neural networks matters;  
 
(1) graph structure of neural networks matters;  
Line 18: Line 28:
  
 
(6) well-performing neural networks have graph structure surprisingly similar to those of real biological neural networks.
 
(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 =
 
= Critique =

Revision as of 15:55, 10 November 2020

Presented By

Xiaolan Xu, Robin Wen, Yue Weng, Beizhen Chang

Introduction

Relational Graph

Parameter Definition

(1) Clustering Coefficient

(2) Average Path Length

Experimental Setup (Section 4 in the paper)

Major Conclusions (Section 5 in the paper)

(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.

Critique