An analysis of the local optima storage capacity of Hopfield network based fitness function models

Citation

Swingler K & Smith L (2014) An analysis of the local optima storage capacity of Hopfield network based fitness function models. In: Nguyen N, Kowalczyk R, Fred A & Joaquim F (eds.) Transactions on Computational Collective Intelligence XVII. Lecture Notes in Computer Science, 8790. Berlin Heidelberg: Springer, pp. 248-271. http://link.springer.com/chapter/10.1007/978-3-662-44994-3_13; https://doi.org/10.1007/978-3-662-44994-3_13

Abstract
A Hopfield Neural Network (HNN) with a new weight update rule can be treated as a second order Estimation of Distribution Algorithm (EDA) or Fitness Function Model (FFM) for solving optimisation problems. The HNN models promising solutions and has a capacity for storing a certain number of local optima as low energy attractors. Solutions are generated by sampling the patterns stored in the attractors. The number of attractors a network can store (its capacity) has an impact on solution diversity and, consequently solution quality. This paper introduces two new HNN learning rules and presents the Hopfield EDA (HEDA), which learns weight values from samples of the fitness function. It investigates the attractor storage capacity of the HEDA and shows it to be equal to that known in the literature for a standard HNN. The relationship between HEDA capacity and linkage order is also investigated.

Keywords
Dynamical systems; Hopfield neural networks; Optimization Energy attractors; Fitness function modeling; Fitness functions; Hopfield Networks; Hopfield neural networks (HNN); Optimisation problems; Solution quality; Storage capacity

People

Professor Leslie Smith

Emeritus Professor, Computing Science

Professor Kevin Swingler

Professor, Computing Science

• Swingler_HEDA_Revision.pdf