arXiv subjects

D. R. C. Dominguez

Publications and source records attributed to D. R. C. Dominguez.

7 recordsLinked to original sources

arXiv2002

Time evolution of the extremely diluted Blume-Emery-Griffiths neural network

The time evolution of the extremely diluted Blume-Emery-Griffiths neural network model is studied, and a detailed equilibrium phase diagram is obtained exhibiting pattern retrieval, fluctuation retrieval and self-sustained activity phases. It is shown that saddle-point solutions associated with fluctuation overlaps slow down considerably the flow of the network states towards the retrieval fixed points. A comparison of the performance with other three-state networks is also presented.

cond-mat.stat-mech↗

arXiv2001

Numerical simulation of a binary communication channel: Comparison between a replica calculation and an exact solution

The mutual information of a single-layer perceptron with $N$ Gaussian inputs and $P$ deterministic binary outputs is studied by numerical simulations. The relevant parameters of the problem are the ratio between the number of output and input units, $α= P/N$, and those describing the two-point correlations between inputs. The main motivation of this work refers to the comparison between the replica computation of the mutual information and an analytical solution valid up to $α\sim O(1)$. The most relevant results are: (1) the simulation supports the validity of the analytical prediction, and (2) it also verifies a previously proposed conjecture that the replica solution interpolates well between large and small values of $α$.

cond-mat.stat-mech↗

arXiv2000

Mutual Information of Three-State Low Activity Diluted Neural Networks with Self-Control

The influence of a macroscopic time-dependent threshold on the retrieval process of three-state extremely diluted neural networks is examined. If the threshold is chosen appropriately in function of the noise and the pattern activity of the network, adapting itself in the course of the time evolution, it guarantees an autonomous functioning of the network. It is found that this self-control mechanism considerably improves the retrieval quality, especially in the limit of low activity, including the storage capacity, the basins of attraction and the information content. The mutual information is shown to be the relevant parameter to study the retrieval quality of such low activity models. Numerical results confirm these observations.

cond-mat.stat-mech↗

arXiv1999

Categorization in fully connected multi-state neural network models

The categorization ability of fully connected neural network models, with either discrete or continuous Q-state units, is studied in this work in replica symmetric mean-field theory. Hierarchically correlated multi-state patterns in a two level structure of ancestors and descendents (examples) are embedded in the network and the categorization task consists in recognizing the ancestors when the network is trained exclusively with their descendents. Explicit results for the dependence of the equilibrium properties of a Q=3-state model and a $Q=\infty$-state model are obtained in the form of phase diagrams and categorization curves. A strong improvement of the categorization ability is found when the network is trained with examples of low activity. The categorization ability is found to be robust to finite threshold and synaptic noise. The Almeida-Thouless lines that limit the validity of the replica-symmetric results, are also obtained.

cond-mat.dis-nn↗

arXiv1998

Inference and Chaos by a Network of Non-monotonic Neurons

The generalization properties of an attractive network of non monotonic neurons which infers concepts from samples are studied. The macroscopic dynamics for the overlap between the state of the neurons with the concepts, well as the activity of the neurons, are obtained and searched for through its numerical behavior. Complex behavior leading from fixed points to chaos through a cascade of bifurcation are found, when we increase the correlation between samples or decrease the activity of the samples and the load of concepts, or tune the threshold of fatigue of the neurons. Both the information dimension and the Liapunov exponent are given, and a phase diagram is built.

cond-mat.stat-mech↗

arXiv1998

Self-control in Sparsely Coded Networks

A complete self-control mechanism is proposed in the dynamics of neural networks through the introduction of a time-dependent threshold, determined in function of both the noise and the pattern activity in the network. Especially for sparsely coded models this mechanism is shown to considerably improve the storage capacity, the basins of attraction and the mutual information content of the network.

cond-mat.stat-mech↗

arXiv1997

Categorization by a three-state attractor neural network

The categorization properties of an attractor network of three-state neurons which infers three-state concepts from examples are studied. The evolution equations governing the parallel dynamics at zero temperature for the overlap between the state of the network and the examples, the state of the network and the concepts as well as the neuron activity are discussed in the limit of extreme dilution. A transition from a retrieval region to a categorization region is found when the number of examples or their correlations are increased. If the pattern activity is small enough, the examples (concepts) are very well retrieved (categorized) for an appropriate choice of the zero-activity threshold of the neurons.

cond-mat.dis-nn↗