Retrieval and Chaos in Extremely Diluted Non-Monotonic Neural Networks
نویسندگان
چکیده
We discuss, in this paper, the dynamical properties of extremely diluted, non-monotonic neural networks. Assuming parallel updating and the Hebb prescription for the synaptic connections, a flow equation for the macroscopic overlap is derived. A rich dynamical phase diagram, was obtained, showing a stable retrieval phase, as well as a cycle two and chaotic behavior. Numerical simulations were performed, showing good agreement with analytical results. Furthermore, the simulations give an additional insight into the microscopic dynamical behavior during the chaotic phase. It is shown that the freezing of individual neuron states is related to the structure of chaotic attractors.
منابع مشابه
Effects of refractory periods in the dynamics of a diluted neural network.
We propose a stochastic dynamics for a neural network which accounts for the effects of the refractory periods ~absolute and relative! in the dynamics of a single neuron. The dynamics can be solved analytically in an extremely diluted network. We found a very rich scenario that presents retrieval phases and a period doubling route to chaos in the attractors of the overlap order parameter. Our m...
متن کاملThermodynamic properties of extremely diluted symmetric Q-Ising neural networks
Using the replica-symmetric mean-field theory approach the thermodynamic and retrieval properties of extremely diluted symmetric Q-Ising neural networks are studied. In particular, capacity-gain parameter and capacity-temperature phase diagrams are derived for Q = 3, 4 and Q = ∞. The zero-temperature results are compared with those obtained from a study of the dynamics of the model. Furthermore...
متن کاملTime evolution of the extremely diluted Blume-Emery-Griffiths neural network.
A study of the time evolution and a stability analysis of the phases in the extremely diluted Blume-Emery-Griffiths neural network model are shown to yield new phase diagrams in which fluctuation retrieval may drive pattern retrieval. It is shown that saddle-point solutions associated with fluctuation overlaps slow down the flow of the network states towards the retrieval fixed points. A compar...
متن کامل1 Retrieval behavior and thermodynamic properties of symmetrically diluted Q - Ising neural networks
The retrieval behavior and thermodynamic properties of symmetrically diluted Q-Ising neural networks are derived and studied in replica-symmetric mean-field theory generalizing earlier works on either the fully connected or the symmetrical extremely diluted network. Capacity-gain parameter phase diagrams are obtained for the Q = 3, Q = 4 and Q = ∞ state networks with uniformly distributed patte...
متن کاملControlling chaos in diluted networks with continuous neurons
Diluted neural networks with continuous neurons and nonmonotonic transfer function are studied, with both fixed and dynamic synapses. A noisy stimulus with periodic variance results in a mechanism for controlling chaos in neural systems with fixed synapses: a proper amount of external perturbation forces the system to behave periodically with the same period as the stimulus.
متن کامل