The stability-capacity diagram of a fully connected neural network, whose bonds take the values 1 and -1 with equal probability, is determined numerically. Two different optimization methods (simulated annealing and tabu search) are used and their relevant features are discussed. The results indicate the existence of a region, in the stability-capacity plane, where replica-symmetry should be broken, within the replica-symmetric phase found by previous, analytical, computations. The critical capacity, consistent with simple arguments on information storage, is found to be less than one.Le diagramme stabilité — capacité d'un réseau de neurones totalement connecté, dont les liens synaptiques ne peuvent prendre que deux valeurs 1 ou — 1, avec l...
<p><b>A.</b> The red plot shows the critical capacity as a function of the size of the basins of att...
In this paper we continue our investigation on the high storage regime of a neural network with Gaus...
The phase diagram of Little's model is determined when the number of stored patterns p grows as ρ = ...
The stability-capacity diagram of a fully connected neural network, whose bonds take the values 1 an...
We study the number p of unbiased random patterns which can be stored in a neural network of N neuro...
The retrieval behavior and thermodynamic properties of symmetrically diluted Q-Ising neural networks...
This paper is divided into four parts. Part 1 contains a survey of three neural networks found in th...
The study of neural networks by physicists started as an extension of the theory of spin glasses. Fo...
We solve the dynamics of Hopfield-type neural networks which store sequences of patterns, close to s...
The information that a pattern of firing in the output layer of a feedforward network of threshold-l...
The information that a pattern of firing in the output layer of a feedforward network of threshold-l...
Abstract. The typical fraction of the space of interactions between each pair of N Ising spins which...
scopus:eid=2-s2.0-78751676189 We study the storage of phase-coded patterns as stable dynamical attra...
AbstractThe focus of the paper is the estimation of the maximum number of states that can be made st...
The importance of the Stability Problem in neurocomputing is discussed, as well as the need for the ...
<p><b>A.</b> The red plot shows the critical capacity as a function of the size of the basins of att...
In this paper we continue our investigation on the high storage regime of a neural network with Gaus...
The phase diagram of Little's model is determined when the number of stored patterns p grows as ρ = ...
The stability-capacity diagram of a fully connected neural network, whose bonds take the values 1 an...
We study the number p of unbiased random patterns which can be stored in a neural network of N neuro...
The retrieval behavior and thermodynamic properties of symmetrically diluted Q-Ising neural networks...
This paper is divided into four parts. Part 1 contains a survey of three neural networks found in th...
The study of neural networks by physicists started as an extension of the theory of spin glasses. Fo...
We solve the dynamics of Hopfield-type neural networks which store sequences of patterns, close to s...
The information that a pattern of firing in the output layer of a feedforward network of threshold-l...
The information that a pattern of firing in the output layer of a feedforward network of threshold-l...
Abstract. The typical fraction of the space of interactions between each pair of N Ising spins which...
scopus:eid=2-s2.0-78751676189 We study the storage of phase-coded patterns as stable dynamical attra...
AbstractThe focus of the paper is the estimation of the maximum number of states that can be made st...
The importance of the Stability Problem in neurocomputing is discussed, as well as the need for the ...
<p><b>A.</b> The red plot shows the critical capacity as a function of the size of the basins of att...
In this paper we continue our investigation on the high storage regime of a neural network with Gaus...
The phase diagram of Little's model is determined when the number of stored patterns p grows as ρ = ...