We study generalizations of the Hopfield model for associative memory which contain interactions of R spins with one another and allow for different weights for input patterns. Using probabilistic considerations we show that stability criteria lead to capacities which increase like powers of N R-1. Investigating numerically the basins of attraction we find behaviour which agrees with theoretical expectations. We introduce the more stringent definition of « coverage-capacity » by requiring the whole phase-space to be covered by the basins of attraction of the input patterns. Even under these conditions we find large numbers of patterns which can be used to design an output spectrum by varying the input weights.Nous étudions des généralisatio...
Abstract-Techniques from,coding theory are applied to study rigor-ously the capacity of the Hopfield...
We introduce a form of the Hopfield model that is able to store an increasing number of biased i.i.d...
Attractor neural networks such as the Hopfield model can be used to model associative memory. An eff...
Networks of threshold automata are random dynamical systems with a large number of attractors, which...
Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfie...
We solve the mean field equations for a stochastic Hopfield network with tem-perature (noise) in the...
Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfie...
We analyze the storage capacity of a variant of the Hopfield model with semantically correlated patt...
We analyze the storage capacity of the Hopfield model with spatially correlated patterns ¸ i (i.e....
The original publication is available at www.springerlink.com . Copyright SpringerThe performance ch...
We study the number p of unbiased random patterns which can be stored in a neural network of N neuro...
The storage capacity of a Q-state Hopfield network is determined via finite size scaling for paralle...
Abstract. The typical fraction of the space of interactions between each pair of N Ising spins which...
Hopfield model of associative memory is studied in this work. In particular, two main problems that ...
The effects of storing p statistically independent but effectively correlated patterns in the Hopfie...
Abstract-Techniques from,coding theory are applied to study rigor-ously the capacity of the Hopfield...
We introduce a form of the Hopfield model that is able to store an increasing number of biased i.i.d...
Attractor neural networks such as the Hopfield model can be used to model associative memory. An eff...
Networks of threshold automata are random dynamical systems with a large number of attractors, which...
Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfie...
We solve the mean field equations for a stochastic Hopfield network with tem-perature (noise) in the...
Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfie...
We analyze the storage capacity of a variant of the Hopfield model with semantically correlated patt...
We analyze the storage capacity of the Hopfield model with spatially correlated patterns ¸ i (i.e....
The original publication is available at www.springerlink.com . Copyright SpringerThe performance ch...
We study the number p of unbiased random patterns which can be stored in a neural network of N neuro...
The storage capacity of a Q-state Hopfield network is determined via finite size scaling for paralle...
Abstract. The typical fraction of the space of interactions between each pair of N Ising spins which...
Hopfield model of associative memory is studied in this work. In particular, two main problems that ...
The effects of storing p statistically independent but effectively correlated patterns in the Hopfie...
Abstract-Techniques from,coding theory are applied to study rigor-ously the capacity of the Hopfield...
We introduce a form of the Hopfield model that is able to store an increasing number of biased i.i.d...
Attractor neural networks such as the Hopfield model can be used to model associative memory. An eff...