The effects of spatially organised data on autoassociative neural networks are investigated in the optimal storage case. An analytical study is possible for weak spatial correlations. It predicts an increasing of the storage capacity $\alpha_c$ and ferromagnetic means for the couplings. Numerical simulations confirm these results for large spatial correlations
A recurrent neural network model storing multiple spatial maps, or “charts,” is analyzed. A network ...
Abstract—We consider the problem of neural association, which deals with the retrieval of a previous...
Short-term synaptic depression and facilitation have been found to greatly influence the performance...
We analyze the storage capacity of the Hopfield model with spatially correlated patterns ¸ i (i.e....
A general mean-field theory is presented for an attractor neural network in which each elementary un...
We study analytically the effect of metrically structured connectivity on the behavior of autoassoci...
The progress in information technologies enables applications of artificial neural networks even in ...
We investigate the properties of an autoassociative network of threshold-linear units whose synaptic...
Autoassociative networks were proposed in the 80's as simplified models of memory function in the br...
Hopfield model is one of the few neural networks for which analytical results can be obtained. Howev...
Hopfield-like neural networks with spatially organized data are studied by a mean-field theory. The ...
Threshold-linear (graded response) units approximate the real firing behaviour of pyramidal neurons ...
The effects of storing p statistically independent but effectively correlated patterns in the Hopfie...
The focus of this work are asociative memories as one type of neural networks. We compare models of ...
On the basis of the evidence, it is suggested that the CA3 stage acts as an autoassociation memory t...
A recurrent neural network model storing multiple spatial maps, or “charts,” is analyzed. A network ...
Abstract—We consider the problem of neural association, which deals with the retrieval of a previous...
Short-term synaptic depression and facilitation have been found to greatly influence the performance...
We analyze the storage capacity of the Hopfield model with spatially correlated patterns ¸ i (i.e....
A general mean-field theory is presented for an attractor neural network in which each elementary un...
We study analytically the effect of metrically structured connectivity on the behavior of autoassoci...
The progress in information technologies enables applications of artificial neural networks even in ...
We investigate the properties of an autoassociative network of threshold-linear units whose synaptic...
Autoassociative networks were proposed in the 80's as simplified models of memory function in the br...
Hopfield model is one of the few neural networks for which analytical results can be obtained. Howev...
Hopfield-like neural networks with spatially organized data are studied by a mean-field theory. The ...
Threshold-linear (graded response) units approximate the real firing behaviour of pyramidal neurons ...
The effects of storing p statistically independent but effectively correlated patterns in the Hopfie...
The focus of this work are asociative memories as one type of neural networks. We compare models of ...
On the basis of the evidence, it is suggested that the CA3 stage acts as an autoassociation memory t...
A recurrent neural network model storing multiple spatial maps, or “charts,” is analyzed. A network ...
Abstract—We consider the problem of neural association, which deals with the retrieval of a previous...
Short-term synaptic depression and facilitation have been found to greatly influence the performance...
DOI
Add to ORKG