Impact of Learning on the Structural Properties of Neural Networks
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 L and C.
Unable to display preview. Download preview PDF.
- 2.Watts, D.J.: Small Worlds. Princeton University Press, Princeton (1999)Google Scholar
- 8.Kim, J.B.: Performance of networks of artificial neurons: The role of clustering. Physical Review E 69, 045101/1-4 (2004)Google Scholar
- 10.McGraw, P.N., Menzinger, M.: Topology and computational performance of attractor neural networks. Physical Review E 68, 047102/1-4 (2003)Google Scholar