Analogical neural networks on correlated random graphs

Physics – Condensed Matter – Disordered Systems and Neural Networks

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Scientific paper

We consider a generalization of the Hopfield model, where the entries of patterns are Gaussian and diluted. We focus on the high-storage regime and we investigate analytically the topological properties of the emergent network, as well as the thermodynamic properties of the model. We find that, by properly tuning the dilution in the pattern entries, the network can recover different topological regimes characterized by peculiar scalings of the average coordination number with respect to the system size. The structure is also shown to exhibit a large degree of cliquishness, even when very sparse. Moreover, we obtain explicitly the replica symmetric free-energy and the self-consistence equations for the overlaps (order parameters of the theory), which turn out to be classical weighted sums of "sub-overlaps" defined on all possible sub-graphs. Finally, a study of criticality is performed through a small-overlap expansion of the self-consistencies and through a whole fluctuation theory developed for their rescaled correlations: both approaches show that the net effect of dilution in pattern entries is to rescale accordingly the critical noise level at which ergodicity breaks down.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Analogical neural networks on correlated random graphs does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Analogical neural networks on correlated random graphs, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Analogical neural networks on correlated random graphs will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-509467

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.