Efficient Hopfield pattern recognition on a scale-free neural network

Abstract

Neural networks are supposed to recognise blurred images (or patterns) of $N$ pixels (bits) each. Application of the network to an initial blurred version of one of $P$ pre-assigned patterns should converge to the correct pattern. In the "standard" Hopfield model, the $N$ "neurons'' are connected to each other via $N^2$ bonds which contain the information on the stored patterns. Thus computer time and memory in general grow with $N^2$. The Hebb rule assigns synaptic coupling strengths proportional to the overlap of the stored patterns at the two coupled neurons. Here we simulate the Hopfield model on the Barabasi-Albert scale-free network, in which each newly added neuron is connected to only $m$ other neurons, and at the end the number of neurons with $q$ neighbours decays as $1/q^3$. Although the quality of retrieval decreases for small $m$, we find good associative memory for $1\ll m\ll N$. Hence, these networks gain a factor $N/m\gg 1$ in the computer memory and time.

8 pages including 4 figures

Cited by in corpus (21)

• The structure and function of complex networks
• Performance of networks of artificial neurons: The role of clustering
• Analytic solution of attractor neural networks on scale-free graphs
• Hierarchical Features of Large-Scale Cortical Connectivity
• Periodic Neural Activity Induced by Network Complexity
• Associative Recall in Non-Randomly Diluted Neuronal Networks
• The Problem of Colliding Networks and its Relation to Cancer
• Effects of degree distribution in mutual synchronization of neural networks
• Growth-Driven Percolations: The Dynamics of Community Formation in Neuronal Systems
• Enhanced storage capacity with errors in scale-free Hopfield neural networks: an analytical study
• Complex Grid Computing
• Topology and Dynamics of Attractor Neural Networks: The Role of Loopiness
• Transient Dynamics of Sparsely Connected Hopfield Neural Networks with Arbitrary Degree Distributions
• Statistical-mechanical iterative algorithms on complex networks
• Competition between ferro-retrieval and anti-ferro orders in a Hopfield-like network model for plant intelligence
• An Analytical Approach to Neuronal Connectivity
• Strength Distribution in Derivative Networks
• On the Importance of Hubs in Hopfield Complex Neuronal Networks under Attack
• Storage Capacity of Extremely Diluted Hopfield Model
• Towards comparative theoretical neuroanatomy of the cerebral cortex
• Parameter Experimental Analysis of the Reservoirs Observers using Echo State Network Approach