Enhanced storage capacity with errors in scale-free Hopfield neural networks: An analytical study
Open Access
- 27 October 2017
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 12 (10), e0184683
- https://doi.org/10.1371/journal.pone.0184683
Abstract
The Hopfield model is a pioneering neural network model with associative memory retrieval. The analytical solution of the model in mean field limit revealed that memories can be retrieved without any error up to a finite storage capacity of O(N), where N is the system size. Beyond the threshold, they are completely lost. Since the introduction of the Hopfield model, the theory of neural networks has been further developed toward realistic neural networks using analog neurons, spiking neurons, etc. Nevertheless, those advances are based on fully connected networks, which are inconsistent with recent experimental discovery that the number of connections of each neuron seems to be heterogeneous, following a heavy-tailed distribution. Motivated by this observation, we consider the Hopfield model on scale-free networks and obtain a different pattern of associative memory retrieval from that obtained on the fully connected network: the storage capacity becomes tremendously enhanced but with some error in the memory retrieval, which appears as the heterogeneity of the connections is increased. Moreover, the error rates are also obtained on several real neural networks and are indeed similar to that on scale-free model networks.Funding Information
- National Research Foundation of Korea (2014R1A3A2069005)
- National Research Foundation of Korea (2015R1A5A7037676)
- Sogang University (201610033.01)
- Sogang University (201710066.01)
This publication has 31 references indexed in Scilit:
- Hubs of brain functional networks are radically reorganized in comatose patientsProceedings of the National Academy of Sciences of the United States of America, 2012
- A small world of weak ties provides optimal global integration of self-similar modules in functional brain networksProceedings of the National Academy of Sciences of the United States of America, 2012
- Percolation Transitions in Scale-Free Networks under the Achlioptas ProcessPhysical Review Letters, 2009
- Small-world and scale-free organization of voxel-based resting-state functional connectivity in the human brainNeuroImage, 2008
- Intrinsic degree-correlations in the static model of scale-free networksZeitschrift für Physik B Condensed Matter, 2006
- Spin-glass phase transition on scale-free networksPhysical Review E, 2005
- Highly Nonrandom Features of Synaptic Connectivity in Local Cortical CircuitsPLoS Biology, 2005
- Analytic solution of attractor neural networks on scale-free graphsJournal of Physics A: General Physics, 2004
- Influence of topology on the performance of a neural networkNeurocomputing, 2004
- Statistical mechanics of neural networks near saturationAnnals of Physics, 1987