A novel chaotic-neuron model is presented by introducing the non-monotonous activation function which is composed of the Legendre function and the Sigmoid function. The reversed bifurcation of the chaotic neuron model is given and analyzed, meanwhile, how do parameters influence the network convergence speed is discussed. Based on the neuron model, the piecewise simulated annealing SLF chaotic ...

| A neural network architecture is discussed which uses Finite Impulse Response (FIR) linear lters to provide dynamic interconnectivity between processing units. The network is applied to a variety of chaotic time series prediction tasks. Phase-space plots of the network dynamics are given to illustrate the reconstruction of underlying chaotic attractors. An example taken from the Santa Fe Inst...

Multimedia communications have become popular in many network services, such as video conferencing, video on demand, and so on. Most multimedia applications require that the attached hosts/routers transmit data through multicasting. In order to provide efficient data routing, routers must provide the multicast capability. In this paper, a self-feedback mechanism controlled by an annealing strat...

In this study, the synchronized response in the chaotic cellular neural network for a grayscale visual stimulus was investigated in the viewpoint of neural coding. Simple gradation patterns were used as visual stimuli and the synchronized response was analyzed by the correlation of the spike firing times. As a result, synchronized responses were observed for the neurons that had similar input v...

This paper proposes a TD (temporal difference) and GA (genetic algorithm) based reinforcement (TDGAR) neural learning scheme for controlling chaotic dynamical systems based on the technique of small perturbations. The TDGAR learning scheme is a new hybrid GA, which integrates the TD prediction method and the GA to fulfill the reinforcement learning task. Structurely, the TDGAR learning system i...

The channel-assignment problem (CAP) in cellular radio networks is known to belong to the class of NPcomplete optimization problems. Many heuristic techniques including Hopfield neural networks (HNN) have been devised for solving the CAP. However, HNNs often suffer from local minima. On the other hand, a recently proposed transiently chaotic neural network (TCNN) has been successfully used in s...

This Letter suggests a new approach to generating chaos via dynamic neural networks. This approach is based on a recently introduced methodology of inverse optimal control for nonlinear systems. Both Chen’s chaotic system and Chua’s circuit are used as examples for demonstration. The control law is derived to force a dynamic neural network to reproduce the intended chaotic attractors. Computer ...

Cooperative coevolution employs different problem decomposition methods to decompose the neural network training problem into subcomponents. The efficiency of a problem decomposition method is dependent on the neural network architecture and the nature of the training problem. The adaptation of problem decomposition methods has been recently proposed which showed that different problem decompos...

There have been much interest in applying noise to neural networks in order to observe their effect on network performance. In our previous research, we have proposed a new modified backpropagation learning algorithm, in which chaotic noise is added into weight update process. By computer simulations, we confirmed that the presence of chaotic noise during weight update process in feedforward ne...

Chaotic dynamical systems are present in the nature in various forms such as the weather, activities in human brain, variation in stock market, flows and turbulence. In order to get a detailed understanding of a system, the modeling and analysis of the system is to be done in an effective way. A recurrent neural network (RNN) structure has been designed for modeling the dynamical system. The ne...