Impact of Learning on the Structural Properties of Neural Networks

Authors:
Branko Šter;Ivan Gabrijel;Andrej Dobnikar
Affiliations:
Faculty of Computer and Information Science, University of Ljubljana, Tržaška 25, 1000 Ljubljana, Slovenia;Faculty of Computer and Information Science, University of Ljubljana, Tržaška 25, 1000 Ljubljana, Slovenia;Faculty of Computer and Information Science, University of Ljubljana, Tržaška 25, 1000 Ljubljana, Slovenia
Venue:
ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part II
Year:
2007

Citing 2
Cited 0

Handbook of Graphs and Networks: From the Genome to the Internet

Handbook of Graphs and Networks: From the Genome to the Internet
On-line identification and reconstruction of finite automata with generalized recurrent neural networks

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We research the impact of the learning process of neural networks (NN) on the structural properties of the derived graphs. A type of recurrent neural network is used (GARNN). A graph is derived from a NN by defining a connection between any pair od nodes having weights in both directions above a certain threshold. We measured structural properties of graphs such as characteristic path lengths (L), clustering coefficients (C) and degree distributions (P). We found that well trained networks differ from badly trained ones in both Land C.