Enhanced storage capacity with errors in scale-free Hopfield neural networks: an analytical study

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.

References in corpus (11)

• Emergence of scaling in random networks
• Scale-free brain functional networks
• Universal Behavior of Load Distribution in Scale-free Networks
• A small-world of weak ties provides optimal global integration of self-similar modules in functional brain networks
• Percolation Transitions in Scale-Free Networks under Achlioptas Process
• Optimisation problems and replica symmetry breaking in finite connectivity spin-glasses
• Efficient Hopfield pattern recognition on a scale-free neural network
• Spin Glass Phase Transition on Scale-Free Networks
• Intrinsic degree-correlations in static model of scale-free networks
• Analytic solution of attractor neural networks on scale-free graphs
• Inverse transitions in a spin-glass model on a scale-free network

Cited by in corpus (2)

• Effective epidemic containment strategy in hypergraphs
• Effect of dilution in asymmetric recurrent neural networks