Article

Grouping synchronization in a pulse-coupled network of chaotic spiking oscillators.

Dept. of Comput. Sci. and Media Eng., Musashi Inst. of Technol., Tokyo, Japan.
IEEE Transactions on Neural Networks (Impact Factor: 2.95). 10/2004; 15(5):1018-26. DOI: 10.1109/TNN.2004.832807
Source: DBLP

ABSTRACT This paper studies a pulse-coupled network consisting of simple chaotic spiking oscillators (CSOs). If a unit oscillator and its neighbor(s) have (almost) the same parameter values, they exhibit in-phase synchronization of chaos. As the parameter values differ, they exhibit asynchronous phenomena. Based on such behavior, some synchronous groups appear partially in the network. Typical phenomena are verified in the laboratory via a simple test circuit. These phenomena can be evaluated numerically by using an effective mapping procedure. We then apply the proposed network to image segmentation. Using a lattice pulse-coupled network via grouping synchronous phenomena, the input image data can be segmented into some sub-regions.

0 Bookmarks
 · 
84 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper the issue of structure based learning of Hopfield like chaotic neural networks is investigated in such a way that all neurons behave in a synchronous manner. By utilizing the idea of structured inverse eigenvalue problem and the sufficient conditions on the coupling weights of a network which guarantee the synchronization of all neuron's outputs, we propose a learning method for tuning the coupling weights of a network where not only synchronize all neuron's outputs with each other but also brings about any desirable topology for the structure of the network. Specifically, this method is evaluated by performing simulations on the scale-free topology.
    Proceedings of the 19th international conference on Neural Information Processing - Volume Part II; 11/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper a new learning rule for the coupling weights tuning of Hopfield like chaotic neural networks is developed in such a way that all neurons behave in a synchronous manner, while the desirable structure of the network is preserved during the learning process. The proposed learning rule is based on sufficient synchronization criteria, on the eigenvalues of the weight matrix belonging to the neural network and the idea of Structured Inverse Eigenvalue Problem. Our developed learning rule not only synchronizes all neuron’s outputs with each other in a desirable topology, but also enables us to enhance the synchronizability of the networks by choosing the appropriate set of weight matrix eigenvalues. Specifically, this method is evaluated by performing simulations on the scale-free topology.
    Cognitive Neurodynamics 04/2014; · 1.77 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In ANN terminology, the synaptic connections are the weights of the neural networks and can be seen as an interaction between neurons. In this paper, we consider two simple neurons which have both self-coupling and non-invertible activation functions. Our studies on these interactions lead to different dynamical behaviors of the network. We show that they can be used as a means of chaos generation or suppression to neuron's outputs when more adaptability or stability is required. This idea may be further used for chaos synchronization of neuron's outputs.
    01/2009;

Full-text (2 Sources)

Download
3 Downloads
Available from