Basin of Attraction of Associative Memory as it Evolves from Random Weights
نویسندگان
چکیده
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 rather small compared to the original Hebb-rule associative memory. In this paper, we present a new version of the previous method trying to control the basin size. As far as we know, this is the rst attempt to address the size of basin of attraction of associative memory by evolutionary processes.
منابع مشابه
Basin of Attraction of Associative Memory as it is Evolved by a Genetic Algorithm
| We are applying genetic algorithms to fully connected neural network model of associative memory, We reported elsewhere that random weight matrix evolves to store some number of patterns only by means of a Genetic Algorithm. And we also reported the Genetic Algorithm can enlarge storage capacity of Hebb-rule associative memory. In those two reports, however, we did not mention about the basin...
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 کاملSearching Real-Valued Synaptic Weights of Hopfield's Associative Memory Using Evolutionary Programming
We apply evolutionary computations to Hop eld model of associative memory. Although there have been a lot of researches which apply evolutionary techniques to layered neural networks, their applications to Hop eld neural networks remain few so far. Previously we reported that a genetic algorithm using discrete encoding chromosomes evolves the Hebb-rule associative memory to enhance its storage ...
متن کاملApplication of an Evolution Strategy to the Hop eld Model of Associative Memory
| We apply evolutionary computations to Hopeld's neural network model of associative memory. In the Hop eld model, almost in nite number of combinations of synaptic weights give a network a function of associative memory. Furthermore, there is a trade-o between the storage capacity and size of basin of attraction. Therefore, the model can be thought of as a test suite of multi-modal and/or mult...
متن کاملRandom Perturbations to Hebbian Synapses of Associative Memory Using a Genetic Algorithm
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 ...
متن کامل