The stability of stochastic delayed cellular neural networks(DCNNs) is investigated in this paper. Under the help of Lyapunov functional and the semimartingale convergence theorem, some sufficient criteria were obtain...The stability of stochastic delayed cellular neural networks(DCNNs) is investigated in this paper. Under the help of Lyapunov functional and the semimartingale convergence theorem, some sufficient criteria were obtained to check the almost sure exponential stability of the DCNNs.展开更多
In the Internet of things, it is of critical importance to fully utilize the potential capacity of the network with efficient medium access control （MAC） mechanisms. In this paper, we study the convergence property ...In the Internet of things, it is of critical importance to fully utilize the potential capacity of the network with efficient medium access control （MAC） mechanisms. In this paper, we study the convergence property of the fixed point formulation of distributed coordination function （DCF）, which is widely used for medium access control in wireless networks. We first Kind that the fixed point could be repelling, which means that it is impossible for an MAC system to converge at its fixed point. Next, we show the existence of periodic points to prove that the fixed point function will oscillate between two periodic points when the fixed point is repelling. We also find that the average of the two periodic points is a close approximation of the fixed point. Based on the findings, we propose an algorithm to compute the fixed point efficiently. Simulation results verify the accuracy and efficiency of our algorithm compared with the previous fixed point computing method.展开更多
In this paper, we present a neural network for solving linear complementarity problem in real time. It possesses a very simple structure for implementation in hardware. In the theoretical aspect, this network is diffe...In this paper, we present a neural network for solving linear complementarity problem in real time. It possesses a very simple structure for implementation in hardware. In the theoretical aspect, this network is different from the existing networks which use the penalty functions or Lagrangians. We prove that the proposed neural network converges globally to the solution set of the problem starting from any initial point. In addition, the stability of the related differential equation system is analyzed and five numerical examples are given to verify the validity of the neural network.展开更多
In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable.
By introducing a deadwzone scheme, a new neural network based adaptive iterative learning control （ILC） （NN-AILC） scheme is presented for nonlinear discrete-time systems, where the NN weights are time-varying. The...By introducing a deadwzone scheme, a new neural network based adaptive iterative learning control （ILC） （NN-AILC） scheme is presented for nonlinear discrete-time systems, where the NN weights are time-varying. The most distinct contribution of the proposed NN-AILC is the relaxation of the identical conditions of initial state and reference trajectory, which are common requirements in traditional ILC problems. Convergence analysis indicates that the tracking error converges to a bounded ball, whose size is determined by the dead-zone nonlinearity. Computer simulations verify the theoretical results.展开更多
基金Sponsored by the National Natural Science Foundation of China (Grant No.10171009) and the Natural Science Foundation of Heilongjiang Province(Grant No.A200605).
文摘The stability of stochastic delayed cellular neural networks(DCNNs) is investigated in this paper. Under the help of Lyapunov functional and the semimartingale convergence theorem, some sufficient criteria were obtained to check the almost sure exponential stability of the DCNNs.
基金supported by the National Basic Research Program of China(No.2011CB302702)the NationalNatural Science Foundation of China(Nos.60803140,60970133,61070187)
文摘In the Internet of things, it is of critical importance to fully utilize the potential capacity of the network with efficient medium access control （MAC） mechanisms. In this paper, we study the convergence property of the fixed point formulation of distributed coordination function （DCF）, which is widely used for medium access control in wireless networks. We first Kind that the fixed point could be repelling, which means that it is impossible for an MAC system to converge at its fixed point. Next, we show the existence of periodic points to prove that the fixed point function will oscillate between two periodic points when the fixed point is repelling. We also find that the average of the two periodic points is a close approximation of the fixed point. Based on the findings, we propose an algorithm to compute the fixed point efficiently. Simulation results verify the accuracy and efficiency of our algorithm compared with the previous fixed point computing method.
基金the State Foundation of Ph.D Units of China(20020141013)the National Natural Science Foundation of China(10471015).
文摘In this paper, we present a neural network for solving linear complementarity problem in real time. It possesses a very simple structure for implementation in hardware. In the theoretical aspect, this network is different from the existing networks which use the penalty functions or Lagrangians. We prove that the proposed neural network converges globally to the solution set of the problem starting from any initial point. In addition, the stability of the related differential equation system is analyzed and five numerical examples are given to verify the validity of the neural network.
基金the National Natural science Foundation of China (10471017)the Basic Research Program of the National Defence Committee of Science,Technology and Industry of China (K1400060406)
文摘In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable.
基金supported by General Program (60774022)State Key Program (60834001) of National Natural Science Foundation of ChinaDoctoral Foundation of Qingdao University of Science & Technology (0022324)
文摘By introducing a deadwzone scheme, a new neural network based adaptive iterative learning control （ILC） （NN-AILC） scheme is presented for nonlinear discrete-time systems, where the NN weights are time-varying. The most distinct contribution of the proposed NN-AILC is the relaxation of the identical conditions of initial state and reference trajectory, which are common requirements in traditional ILC problems. Convergence analysis indicates that the tracking error converges to a bounded ball, whose size is determined by the dead-zone nonlinearity. Computer simulations verify the theoretical results.
