Random Perturbations to Hebbian Synapses of Associative Memory Using a Genetic Algorithm
نویسندگان
چکیده
We apply evolutionary algorithms to Hop eld model of associative memory. Previously we reported that a genetic algorithm using ternary chromosomes evolves the Hebb-rule associative memory to enhance its storage capacity by pruning some connections. This paper describes a genetic algorithm using real-encoded chromosomes which successfully evolves over-loaded Hebbian synaptic weights to function as an associative memory. The goal of this study is to shed new light on the analysis of the Hop eld model, which also enables us to use the model as more challenging test suite for evolutionary computations.
منابع مشابه
Basin of Attraction of Associative Memory as it Evolves from Random Weights
We apply genetic algorithms to fully connected Hop eld associative memory networks. Previously, we reported that a genetic algorithm can evolve networks with random synaptic weights to store some number of patterns by pruning some of its synapses. The associative memory capacity obtained in that experiment was around 16% of the number of neurons. However the size of basin of attraction was rath...
متن کاملDoes Diploidy A ect Evolutions of Hop eld Associative Memory ?
We apply genetic algorithms to the Hop eld's neural network model of associative memory. Previously, we observed that random synaptic weights of a network evolved to create the xed point attractors corresponding to a set of given patterns to be stored. In that simulation, a weight con guration was expressed as a sequence of genes which might be called a haploid chromosome. Then a population of ...
متن کاملHow Real-valued Random Synapses Evolve Toward Symmetry with Diploid Chromosomes?
We apply genetic algorithms to the Hop eld's neural network model of associative memory. Previously, we observed that random synaptic weights of a network evolved to create the xed point attractors in pattern space exactly at the locations corresponding to a set of given patterns to be stored. In that simulation, a weight con guration was represented as a sequence of genes which might be called...
متن کاملEvolved Asymmetry and Dilution of Random Synaptic Weights in Hop eld Network Turn a Spin-glass Phase into Associative Memory
We apply evolutionary computations to Hop eld's neural network model of associative memory. Previously, we reported that a genetic algorithm can enlarge the Hebb rule associative memory by pruning some of over-loaded Hebbian synaptic weights. In this paper, we present the genetic algorithm also evolves random synaptic weights to store some number of patterns.
متن کاملHop eld Model of Associative Memory as a Test Function of Evolutionary Computations
We apply genetic algorithms to Hop eld's neural network model of associative memory. Previously, using ternary chromosomes, we successfully evolved both random weight matrix and over-loaded Hebbian weight matrix to function as an associative memory. In this paper, we present a real-encoded genetic algorithm to evolve random synaptic weights to store some number of patterns as associative memory...
متن کامل